Integrate mainline.

p4raw-id: //depot/perlio@9904

121 files changed, 921 insertions, 309 deletions

diff --git a/INSTALL b/INSTALL
index 4f5c039861..39d28d6341 100644
--- a/INSTALL
+++ b/INSTALL
@@ -896,8 +896,8 @@ You can elect to build a shared libperl by
 
 To build a shared libperl, the environment variable controlling shared
 library search (LD_LIBRARY_PATH in most systems, DYLD_LIBRARY_PATH for
-NeXTSTEP/OPENSTEP/Darwin, LIBRARY_PATH for BeOS, SHLIB_PATH for
-HP-UX, LIBPATH for AIX, PATH for Cygwin) must be set up to include
+NeXTSTEP/OPENSTEP/Darwin, LIBRARY_PATH for BeOS, LD_LIBRARY_PATH/SHLIB_PATH
+for HP-UX, LIBPATH for AIX, PATH for Cygwin) must be set up to include
 the Perl build directory because that's where the shared libperl will
 be created.  Configure arranges makefile to have the correct shared
 library search settings.
diff --git a/MANIFEST b/MANIFEST
index 33e69ebb30..988302e628 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -888,7 +888,7 @@ lib/unicode/ArabLnkGrp.pl			Unicode character database
 lib/unicode/ArabShap.txt			Unicode character database
 lib/unicode/BidiMirr.txt			Unicode character database
 lib/unicode/Bidirectional.pl			Unicode character database
-lib/unicode/Block.pl				Unicode character database
+lib/unicode/Blocks.pl				Unicode character database
 lib/unicode/Blocks.txt				Unicode character database
 lib/unicode/CaseFold.txt			Unicode character database
 lib/unicode/Category.pl				Unicode character database
@@ -896,93 +896,103 @@ lib/unicode/CombiningClass.pl			Unicode character database
 lib/unicode/CompExcl.txt			Unicode character database
 lib/unicode/Decomposition.pl			Unicode character database
 lib/unicode/EAWidth.txt				Unicode character database
-lib/unicode/In/AlphabeticPresentationForms.pl	Unicode character database
-lib/unicode/In/Arabic.pl			Unicode character database
-lib/unicode/In/ArabicPresentationForms-A.pl	Unicode character database
-lib/unicode/In/ArabicPresentationForms-B.pl	Unicode character database
-lib/unicode/In/Armenian.pl			Unicode character database
-lib/unicode/In/Arrows.pl			Unicode character database
-lib/unicode/In/BasicLatin.pl			Unicode character database
-lib/unicode/In/Bengali.pl			Unicode character database
-lib/unicode/In/BlockElements.pl			Unicode character database
-lib/unicode/In/Bopomofo.pl			Unicode character database
-lib/unicode/In/BopomofoExtended.pl		Unicode character database
-lib/unicode/In/BoxDrawing.pl			Unicode character database
-lib/unicode/In/BraillePatterns.pl		Unicode character database
-lib/unicode/In/CJKCompatibility.pl		Unicode character database
-lib/unicode/In/CJKCompatibilityForms.pl		Unicode character database
-lib/unicode/In/CJKCompatibilityIdeographs.pl	Unicode character database
-lib/unicode/In/CJKRadicalsSupplement.pl		Unicode character database
-lib/unicode/In/CJKSymbolsandPunctuation.pl	Unicode character database
-lib/unicode/In/CJKUnifiedIdeographs.pl		Unicode character database
-lib/unicode/In/CJKUnifiedIdeographsExtensionA.pl	Unicode character database
-lib/unicode/In/Cherokee.pl			Unicode character database
-lib/unicode/In/CombiningDiacriticalMarks.pl	Unicode character database
-lib/unicode/In/CombiningHalfMarks.pl		Unicode character database
-lib/unicode/In/CombiningMarksforSymbols.pl	Unicode character database
-lib/unicode/In/ControlPictures.pl		Unicode character database
-lib/unicode/In/CurrencySymbols.pl		Unicode character database
-lib/unicode/In/Cyrillic.pl			Unicode character database
-lib/unicode/In/Devanagari.pl			Unicode character database
-lib/unicode/In/Dingbats.pl			Unicode character database
-lib/unicode/In/EnclosedAlphanumerics.pl		Unicode character database
-lib/unicode/In/EnclosedCJKLettersandMonths.pl	Unicode character database
-lib/unicode/In/Ethiopic.pl			Unicode character database
-lib/unicode/In/GeneralPunctuation.pl		Unicode character database
-lib/unicode/In/GeometricShapes.pl		Unicode character database
-lib/unicode/In/Georgian.pl			Unicode character database
-lib/unicode/In/Greek.pl				Unicode character database
-lib/unicode/In/GreekExtended.pl			Unicode character database
-lib/unicode/In/Gujarati.pl			Unicode character database
-lib/unicode/In/Gurmukhi.pl			Unicode character database
-lib/unicode/In/HalfwidthandFullwidthForms.pl	Unicode character database
-lib/unicode/In/HangulCompatibilityJamo.pl	Unicode character database
-lib/unicode/In/HangulJamo.pl			Unicode character database
-lib/unicode/In/HangulSyllables.pl		Unicode character database
-lib/unicode/In/Hebrew.pl			Unicode character database
-lib/unicode/In/HighPrivateUseSurrogates.pl	Unicode character database
-lib/unicode/In/HighSurrogates.pl		Unicode character database
-lib/unicode/In/Hiragana.pl			Unicode character database
-lib/unicode/In/IPAExtensions.pl			Unicode character database
-lib/unicode/In/IdeographicDescriptionCharacters.pl	Unicode character database
-lib/unicode/In/Kanbun.pl			Unicode character database
-lib/unicode/In/KangxiRadicals.pl		Unicode character database
-lib/unicode/In/Kannada.pl			Unicode character database
-lib/unicode/In/Katakana.pl			Unicode character database
-lib/unicode/In/Khmer.pl				Unicode character database
-lib/unicode/In/Lao.pl				Unicode character database
-lib/unicode/In/Latin-1Supplement.pl		Unicode character database
-lib/unicode/In/LatinExtended-A.pl		Unicode character database
-lib/unicode/In/LatinExtended-B.pl		Unicode character database
-lib/unicode/In/LatinExtendedAdditional.pl	Unicode character database
-lib/unicode/In/LetterlikeSymbols.pl		Unicode character database
-lib/unicode/In/LowSurrogates.pl			Unicode character database
-lib/unicode/In/Malayalam.pl			Unicode character database
-lib/unicode/In/MathematicalOperators.pl		Unicode character database
-lib/unicode/In/MiscellaneousSymbols.pl		Unicode character database
-lib/unicode/In/MiscellaneousTechnical.pl	Unicode character database
-lib/unicode/In/Mongolian.pl			Unicode character database
-lib/unicode/In/Myanmar.pl			Unicode character database
-lib/unicode/In/NumberForms.pl			Unicode character database
-lib/unicode/In/Ogham.pl				Unicode character database
-lib/unicode/In/OpticalCharacterRecognition.pl	Unicode character database
-lib/unicode/In/Oriya.pl				Unicode character database
-lib/unicode/In/PrivateUse.pl			Unicode character database
-lib/unicode/In/Runic.pl				Unicode character database
-lib/unicode/In/Sinhala.pl			Unicode character database
-lib/unicode/In/SmallFormVariants.pl		Unicode character database
-lib/unicode/In/SpacingModifierLetters.pl	Unicode character database
-lib/unicode/In/Specials.pl			Unicode character database
-lib/unicode/In/SuperscriptsandSubscripts.pl	Unicode character database
-lib/unicode/In/Syriac.pl			Unicode character database
-lib/unicode/In/Tamil.pl				Unicode character database
-lib/unicode/In/Telugu.pl			Unicode character database
-lib/unicode/In/Thaana.pl			Unicode character database
-lib/unicode/In/Thai.pl				Unicode character database
-lib/unicode/In/Tibetan.pl			Unicode character database
-lib/unicode/In/UnifiedCanadianAboriginalSyllabics.pl	Unicode character database
-lib/unicode/In/YiRadicals.pl			Unicode character database
-lib/unicode/In/YiSyllables.pl			Unicode character database
+lib/unicode/In.pl				Unicode character database
+lib/unicode/In/0.pl				Unicode character database
+lib/unicode/In/1.pl				Unicode character database
+lib/unicode/In/2.pl				Unicode character database
+lib/unicode/In/3.pl				Unicode character database
+lib/unicode/In/4.pl				Unicode character database
+lib/unicode/In/5.pl				Unicode character database
+lib/unicode/In/6.pl				Unicode character database
+lib/unicode/In/7.pl				Unicode character database
+lib/unicode/In/8.pl				Unicode character database
+lib/unicode/In/9.pl				Unicode character database
+lib/unicode/In/10.pl				Unicode character database
+lib/unicode/In/11.pl				Unicode character database
+lib/unicode/In/12.pl				Unicode character database
+lib/unicode/In/13.pl				Unicode character database
+lib/unicode/In/14.pl				Unicode character database
+lib/unicode/In/15.pl				Unicode character database
+lib/unicode/In/16.pl				Unicode character database
+lib/unicode/In/17.pl				Unicode character database
+lib/unicode/In/18.pl				Unicode character database
+lib/unicode/In/19.pl				Unicode character database
+lib/unicode/In/20.pl				Unicode character database
+lib/unicode/In/21.pl				Unicode character database
+lib/unicode/In/22.pl				Unicode character database
+lib/unicode/In/23.pl				Unicode character database
+lib/unicode/In/24.pl				Unicode character database
+lib/unicode/In/25.pl				Unicode character database
+lib/unicode/In/26.pl				Unicode character database
+lib/unicode/In/27.pl				Unicode character database
+lib/unicode/In/28.pl				Unicode character database
+lib/unicode/In/29.pl				Unicode character database
+lib/unicode/In/30.pl				Unicode character database
+lib/unicode/In/31.pl				Unicode character database
+lib/unicode/In/32.pl				Unicode character database
+lib/unicode/In/33.pl				Unicode character database
+lib/unicode/In/34.pl				Unicode character database
+lib/unicode/In/35.pl				Unicode character database
+lib/unicode/In/36.pl				Unicode character database
+lib/unicode/In/37.pl				Unicode character database
+lib/unicode/In/38.pl				Unicode character database
+lib/unicode/In/39.pl				Unicode character database
+lib/unicode/In/40.pl				Unicode character database
+lib/unicode/In/41.pl				Unicode character database
+lib/unicode/In/42.pl				Unicode character database
+lib/unicode/In/43.pl				Unicode character database
+lib/unicode/In/44.pl				Unicode character database
+lib/unicode/In/45.pl				Unicode character database
+lib/unicode/In/46.pl				Unicode character database
+lib/unicode/In/47.pl				Unicode character database
+lib/unicode/In/48.pl				Unicode character database
+lib/unicode/In/49.pl				Unicode character database
+lib/unicode/In/50.pl				Unicode character database
+lib/unicode/In/51.pl				Unicode character database
+lib/unicode/In/52.pl				Unicode character database
+lib/unicode/In/53.pl				Unicode character database
+lib/unicode/In/54.pl				Unicode character database
+lib/unicode/In/55.pl				Unicode character database
+lib/unicode/In/56.pl				Unicode character database
+lib/unicode/In/57.pl				Unicode character database
+lib/unicode/In/58.pl				Unicode character database
+lib/unicode/In/59.pl				Unicode character database
+lib/unicode/In/60.pl				Unicode character database
+lib/unicode/In/61.pl				Unicode character database
+lib/unicode/In/62.pl				Unicode character database
+lib/unicode/In/63.pl				Unicode character database
+lib/unicode/In/64.pl				Unicode character database
+lib/unicode/In/65.pl				Unicode character database
+lib/unicode/In/66.pl				Unicode character database
+lib/unicode/In/67.pl				Unicode character database
+lib/unicode/In/68.pl				Unicode character database
+lib/unicode/In/69.pl				Unicode character database
+lib/unicode/In/70.pl				Unicode character database
+lib/unicode/In/71.pl				Unicode character database
+lib/unicode/In/72.pl				Unicode character database
+lib/unicode/In/73.pl				Unicode character database
+lib/unicode/In/74.pl				Unicode character database
+lib/unicode/In/75.pl				Unicode character database
+lib/unicode/In/76.pl				Unicode character database
+lib/unicode/In/77.pl				Unicode character database
+lib/unicode/In/78.pl				Unicode character database
+lib/unicode/In/79.pl				Unicode character database
+lib/unicode/In/80.pl				Unicode character database
+lib/unicode/In/81.pl				Unicode character database
+lib/unicode/In/82.pl				Unicode character database
+lib/unicode/In/83.pl				Unicode character database
+lib/unicode/In/84.pl				Unicode character database
+lib/unicode/In/85.pl				Unicode character database
+lib/unicode/In/86.pl				Unicode character database
+lib/unicode/In/87.pl				Unicode character database
+lib/unicode/In/88.pl				Unicode character database
+lib/unicode/In/89.pl				Unicode character database
+lib/unicode/In/90.pl				Unicode character database
+lib/unicode/In/91.pl				Unicode character database
+lib/unicode/In/92.pl				Unicode character database
+lib/unicode/In/93.pl				Unicode character database
+lib/unicode/In/94.pl				Unicode character database
+lib/unicode/In/95.pl				Unicode character database
 lib/unicode/Index.txt				Unicode character database
 lib/unicode/Is/ASCII.pl				Unicode character database
 lib/unicode/Is/Alnum.pl				Unicode character database
diff --git a/doop.c b/doop.c
index d7baecc792..755cbfd16a 100644
--- a/doop.c
+++ b/doop.c
@@ -344,7 +344,7 @@ S_do_trans_simple_utf8(pTHX_ SV *sv)/* SPC - OK */
     }
 
     while (s < send) {
-	if ((uv = swash_fetch(rv, s)) < none) {
+	if ((uv = swash_fetch(rv, s, TRUE)) < none) {
 	    s += UTF8SKIP(s);
 	    matches++;
 	    d = uvuni_to_utf8(d, uv);
@@ -423,7 +423,7 @@ S_do_trans_count_utf8(pTHX_ SV *sv)/* SPC - OK */
     send = s + len;
 
     while (s < send) {
-	if ((uv = swash_fetch(rv, s)) < none || uv == extra)
+	if ((uv = swash_fetch(rv, s, TRUE)) < none || uv == extra)
 	    matches++;
 	s += UTF8SKIP(s);
     }
@@ -491,7 +491,7 @@ S_do_trans_complex_utf8(pTHX_ SV *sv) /* SPC - NOT OK */
     if (squash) {
 	UV puv = 0xfeedface;
 	while (s < send) {
-	    uv = swash_fetch(rv, s);
+	    uv = swash_fetch(rv, s, TRUE);
 	
 	    if (d > dend) {
 	        STRLEN clen = d - dstart;
@@ -546,7 +546,7 @@ S_do_trans_complex_utf8(pTHX_ SV *sv) /* SPC - NOT OK */
     }
     else {
 	while (s < send) {
-	    uv = swash_fetch(rv, s);
+	    uv = swash_fetch(rv, s, TRUE);
 	    if (d > dend) {
 	        STRLEN clen = d - dstart;
 		STRLEN nlen = dend - dstart + len + UTF8_MAXLEN;
diff --git a/embed.h b/embed.h
index 887e9eb66d..dd5d658969 100644
--- a/embed.h
+++ b/embed.h
@@ -2216,7 +2216,7 @@
 #define sv_vsetpvfn(a,b,c,d,e,f,g)	Perl_sv_vsetpvfn(aTHX_ a,b,c,d,e,f,g)
 #define str_to_version(a)	Perl_str_to_version(aTHX_ a)
 #define swash_init(a,b,c,d,e)	Perl_swash_init(aTHX_ a,b,c,d,e)
-#define swash_fetch(a,b)	Perl_swash_fetch(aTHX_ a,b)
+#define swash_fetch(a,b,c)	Perl_swash_fetch(aTHX_ a,b,c)
 #define taint_env()		Perl_taint_env(aTHX)
 #define taint_proper(a,b)	Perl_taint_proper(aTHX_ a,b)
 #define to_utf8_lower(a)	Perl_to_utf8_lower(aTHX_ a)
diff --git a/embed.pl b/embed.pl
index 9e272b8572..fcaaaed90a 100755
--- a/embed.pl
+++ b/embed.pl
@@ -2089,7 +2089,7 @@ Apd	|void	|sv_vsetpvfn	|SV* sv|const char* pat|STRLEN patlen \
 Ap	|NV	|str_to_version	|SV *sv
 Ap	|SV*	|swash_init	|char* pkg|char* name|SV* listsv \
 				|I32 minbits|I32 none
-Ap	|UV	|swash_fetch	|SV *sv|U8 *ptr
+Ap	|UV	|swash_fetch	|SV *sv|U8 *ptr|bool do_utf8
 Ap	|void	|taint_env
 Ap	|void	|taint_proper	|const char* f|const char* s
 Ap	|UV	|to_utf8_lower	|U8 *p
diff --git a/ext/B/B/Deparse.pm b/ext/B/B/Deparse.pm
index e8ebb39774..7e57a58b51 100644
--- a/ext/B/B/Deparse.pm
+++ b/ext/B/B/Deparse.pm
@@ -1024,7 +1024,22 @@ sub scopeop {
     }
 }
 
-sub pp_scope { scopeop(0, @_); }
+sub invoker {
+    my $caller = (caller(2))[3];
+    if ($caller eq "B::Deparse::deparse") {
+	return (caller(3))[3];
+    }
+    else {
+	return $caller;
+    }
+}
+
+sub pp_scope {
+    my ($self, $op, $cx) = @_;
+    my $body = scopeop(0, @_);
+    return $body if $cx > 0 || invoker() ne "B::Deparse::lineseq";
+    return "do {\n\t$body\n\b};";
+}
 sub pp_lineseq { scopeop(0, @_); }
 sub pp_leave { scopeop(1, @_); }
 
@@ -2347,6 +2362,8 @@ sub pp_null {
 	return $self->maybe_parens($self->deparse($op->first, 20) . " =~ "
 				   . $self->deparse($op->first->sibling, 20),
 				   $cx, 20);
+    } elsif ($op->flags & OPf_SPECIAL && $cx == 0 && !$op->targ) {
+	return "do {\n\t". $self->deparse($op->first, $cx) ."\n\b};";
     } else {
 	return $self->deparse($op->first, $cx);
     }
diff --git a/ext/IO/lib/IO/Seekable.pm b/ext/IO/lib/IO/Seekable.pm
index d3dfa1e697..95dd4d0c36 100644
--- a/ext/IO/lib/IO/Seekable.pm
+++ b/ext/IO/lib/IO/Seekable.pm
@@ -41,7 +41,7 @@ corresponding built-in functions:
 
 =over 4
 
-=item $io->setpos ( POS, WHENCE )
+=item $io->seek ( POS, WHENCE )
 
 Seek the IO::File to position POS, relative to WHENCE:
 
@@ -55,7 +55,7 @@ POS is absolute position. (Seek relative to the start of the file)
 
 POS is an offset from the current position. (Seek relative to current)
 
-=item WHENCE=1 (SEEK_END)
+=item WHENCE=2 (SEEK_END)
 
 POS is an offset from the end of the file. (Seek relative to end)
 
diff --git a/hints/hpux.sh b/hints/hpux.sh
index 8623715654..da481dac38 100644
--- a/hints/hpux.sh
+++ b/hints/hpux.sh
@@ -37,24 +37,12 @@ echo "Archname is $archname"
 
 ### HP-UX OS specific behaviour
 
-case "$ccflags" in
-'') cc_cppflags='' ;;
-*)  set `echo " $ccflags " | sed -e 's/ -A[ea] / /g' -e 's/ -D_HPUX_SOURCE / /'`
-    cc_cppflags="$* -D_HPUX_SOURCE"
-    ;;
-esac
-ccflags="-Ae $cc_cppflags"
-cppflags="-Aa -D__STDC_EXT__ $cc_cppflags"
-
-case "$prefix" in
-    "") prefix='/opt/perl5' ;;
-    esac
-
 # -ldbm is obsolete and should not be used
 # -lBSD contains BSD-style duplicates of SVR4 routines that cause confusion
 # -lPW is obsolete and should not be used
 # The libraries crypt, malloc, ndir, and net are empty.
-set `echo " $libswanted " | sed -e 's/ ld / /' -e 's/ dbm / /' -e 's/ BSD / /' -e 's/ PW / /'`
+set `echo "X $libswanted " | sed -e 's/ ld / /' -e 's/ dbm / /' -e 's/ BSD / /' -e 's/ PW / /'`
+shift
 libswanted="$*"
 
 # By setting the deferred flag below, this means that if you run perl
@@ -71,17 +59,30 @@ libswanted="$*"
 ccdlflags="-Wl,-E -Wl,-B,deferred $ccdlflags"
 
 cc=${cc:-cc}
+ar=/usr/bin/ar	# Yes, truly override.  We do not want the GNU ar.
+full_ar=$ar	# I repeat, no GNU ar.  arrr.
 
-ar=/usr/bin/ar # Yes, truly override.  We do not want the GNU ar.
-full_ar=$ar    # I repeat, no GNU ar.  arrr.
+set `echo "X $ccflags " | sed -e 's/ -A[ea] / /' -e 's/ -D_HPUX_SOURCE / /'`
+shift
+	cc_cppflags="$* -D_HPUX_SOURCE"
+cppflags="-Aa -D__STDC_EXT__ $cc_cppflags"
+
+case "$prefix" in
+    "") prefix='/opt/perl5' ;;
+    esac
 
 case `$cc -v 2>&1`"" in
-    *gcc*)  ccisgcc="$define" ;;
-    *)      ccisgcc=''
-	    ccversion=`which cc | xargs what | awk '/Compiler/{print $2}'`
+    *gcc*)  ccisgcc="$define"
+	    ccflags="$cc_cppflags"
 	    case "`getconf KERNEL_BITS 2>/dev/null`" in
-		*64*) ldflags="$ldflags -Wl,+vnocompatwarnings" ;;
+		*64*)   ldflags="$ldflags -Wl,+vnocompatwarnings"
+			ccflags="$ccflags -Wl,+vnocompatwarnings -Wa,+DA2.0"
+			;;
 		esac
+	    ;;
+    *)      ccisgcc=''
+	    ccversion=`which cc | xargs what | awk '/Compiler/{print $2}'`
+	    ccflags="-Ae $cc_cppflags"
 	    case "$d_casti32" in
 		"") d_casti32='undef' ;;
 		esac
@@ -175,37 +176,54 @@ case "$ccisgcc" in
     $define|true|[Yy])
 	
 	case "$optimize" in
-	    "") optimize="-g -O" ;;
+	    "")           optimize="-g -O" ;;
+	    *O[3456789]*) optimize=`echo "$optimize" | sed -e 's/O[3-9]/O2/'` ;;
 	    esac
-	ld="$cc"
+	#ld="$cc"
+	ld="/usr/bin/ld"
 	cccdlflags='-fPIC'
-	lddlflags='-shared'
+	#lddlflags='-shared'
+	lddlflags='-b +vnocompatwarnings'
+	case "$optimize" in
+	    *-g*-O*|*-O*-g*)
+		# gcc without gas will not accept -g
+		echo "main(){}">try.c
+		case "`$cc $optimize -c try.c 2>&1`" in
+		    *"-g option disabled"*)
+			set `echo "X $optimize " | sed -e 's/ -g / /'`
+			shift
+			optimize="$*"
+			;;
+		    esac
+		;;
+	    esac
 	;;
 
     *)	# HP's compiler cannot combine -g and -O
 	case "$optimize" in
-	    "") optimize="-O" ;;
+	    "")           optimize="-O" ;;
+	    *O[3456789]*) optimize=`echo "$optimize" | sed -e 's/O[3-9]/O2/'` ;;
 	    esac
 	ld=/usr/bin/ld
 	cccdlflags='+Z'
-	lddlflags='-b'
+	lddlflags='-b +vnocompatwarnings'
 	;;
     esac
 
 
 ## LARGEFILES
 
-case "$uselargefiles-$ccisgcc" in
-    "$define-$define"|'-define') 
-	cat <<EOM >&4
-
-*** I'm ignoring large files for this build because
-*** I don't know how to do use large files in HP-UX using gcc.
-
-EOM
-	uselargefiles="$undef"
-	;;
-    esac
+#case "$uselargefiles-$ccisgcc" in
+#    "$define-$define"|'-define') 
+#	cat <<EOM >&4
+#
+#*** I'm ignoring large files for this build because
+#*** I don't know how to do use large files in HP-UX using gcc.
+#
+#EOM
+#	uselargefiles="$undef"
+#	;;
+#    esac
 
 cat >UU/uselargefiles.cbu <<'EOCBU'
 # This script UU/uselargefiles.cbu will get 'called-back' by Configure 
diff --git a/lib/unicode/Blocks.pl b/lib/unicode/Blocks.pl
new file mode 100644
index 0000000000..ef60058ba3
--- /dev/null
+++ b/lib/unicode/Blocks.pl
@@ -0,0 +1,203 @@
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by mktables.PL from e.g. Unicode.txt.
+# Any changes made here will be lost!
+return <<'END';
+0000	007F	Basic Latin
+# In/0.pl BasicLatin
+0080	00FF	Latin-1 Supplement
+# In/1.pl Latin1Supplement
+0100	017F	Latin Extended-A
+# In/2.pl LatinExtendedA
+0180	024F	Latin Extended-B
+# In/3.pl LatinExtendedB
+0250	02AF	IPA Extensions
+# In/4.pl IPAExtensions
+02B0	02FF	Spacing Modifier Letters
+# In/5.pl SpacingModifierLetters
+0300	036F	Combining Diacritical Marks
+# In/6.pl CombiningDiacriticalMarks
+0370	03FF	Greek
+# In/7.pl Greek
+0400	04FF	Cyrillic
+# In/8.pl Cyrillic
+0530	058F	Armenian
+# In/9.pl Armenian
+0590	05FF	Hebrew
+# In/10.pl Hebrew
+0600	06FF	Arabic
+# In/11.pl Arabic
+0700	074F	Syriac  
+# In/12.pl Syriac
+0780	07BF	Thaana
+# In/13.pl Thaana
+0900	097F	Devanagari
+# In/14.pl Devanagari
+0980	09FF	Bengali
+# In/15.pl Bengali
+0A00	0A7F	Gurmukhi
+# In/16.pl Gurmukhi
+0A80	0AFF	Gujarati
+# In/17.pl Gujarati
+0B00	0B7F	Oriya
+# In/18.pl Oriya
+0B80	0BFF	Tamil
+# In/19.pl Tamil
+0C00	0C7F	Telugu
+# In/20.pl Telugu
+0C80	0CFF	Kannada
+# In/21.pl Kannada
+0D00	0D7F	Malayalam
+# In/22.pl Malayalam
+0D80	0DFF	Sinhala
+# In/23.pl Sinhala
+0E00	0E7F	Thai
+# In/24.pl Thai
+0E80	0EFF	Lao
+# In/25.pl Lao
+0F00	0FFF	Tibetan
+# In/26.pl Tibetan
+1000	109F	Myanmar 
+# In/27.pl Myanmar
+10A0	10FF	Georgian
+# In/28.pl Georgian
+1100	11FF	Hangul Jamo
+# In/29.pl HangulJamo
+1200	137F	Ethiopic
+# In/30.pl Ethiopic
+13A0	13FF	Cherokee
+# In/31.pl Cherokee
+1400	167F	Unified Canadian Aboriginal Syllabics
+# In/32.pl UnifiedCanadianAboriginalSyllabics
+1680	169F	Ogham
+# In/33.pl Ogham
+16A0	16FF	Runic
+# In/34.pl Runic
+1780	17FF	Khmer
+# In/35.pl Khmer
+1800	18AF	Mongolian
+# In/36.pl Mongolian
+1E00	1EFF	Latin Extended Additional
+# In/37.pl LatinExtendedAdditional
+1F00	1FFF	Greek Extended
+# In/38.pl GreekExtended
+2000	206F	General Punctuation
+# In/39.pl GeneralPunctuation
+2070	209F	Superscripts and Subscripts
+# In/40.pl SuperscriptsandSubscripts
+20A0	20CF	Currency Symbols
+# In/41.pl CurrencySymbols
+20D0	20FF	Combining Marks for Symbols
+# In/42.pl CombiningMarksforSymbols
+2100	214F	Letterlike Symbols
+# In/43.pl LetterlikeSymbols
+2150	218F	Number Forms
+# In/44.pl NumberForms
+2190	21FF	Arrows
+# In/45.pl Arrows
+2200	22FF	Mathematical Operators
+# In/46.pl MathematicalOperators
+2300	23FF	Miscellaneous Technical
+# In/47.pl MiscellaneousTechnical
+2400	243F	Control Pictures
+# In/48.pl ControlPictures
+2440	245F	Optical Character Recognition
+# In/49.pl OpticalCharacterRecognition
+2460	24FF	Enclosed Alphanumerics
+# In/50.pl EnclosedAlphanumerics
+2500	257F	Box Drawing
+# In/51.pl BoxDrawing
+2580	259F	Block Elements
+# In/52.pl BlockElements
+25A0	25FF	Geometric Shapes
+# In/53.pl GeometricShapes
+2600	26FF	Miscellaneous Symbols
+# In/54.pl MiscellaneousSymbols
+2700	27BF	Dingbats
+# In/55.pl Dingbats
+2800	28FF	Braille Patterns
+# In/56.pl BraillePatterns
+2E80	2EFF	CJK Radicals Supplement
+# In/57.pl CJKRadicalsSupplement
+2F00	2FDF	Kangxi Radicals
+# In/58.pl KangxiRadicals
+2FF0	2FFF	Ideographic Description Characters
+# In/59.pl IdeographicDescriptionCharacters
+3000	303F	CJK Symbols and Punctuation
+# In/60.pl CJKSymbolsandPunctuation
+3040	309F	Hiragana
+# In/61.pl Hiragana
+30A0	30FF	Katakana
+# In/62.pl Katakana
+3100	312F	Bopomofo
+# In/63.pl Bopomofo
+3130	318F	Hangul Compatibility Jamo
+# In/64.pl HangulCompatibilityJamo
+3190	319F	Kanbun
+# In/65.pl Kanbun
+31A0	31BF	Bopomofo Extended
+# In/66.pl BopomofoExtended
+3200	32FF	Enclosed CJK Letters and Months
+# In/67.pl EnclosedCJKLettersandMonths
+3300	33FF	CJK Compatibility
+# In/68.pl CJKCompatibility
+3400	4DB5	CJK Unified Ideographs Extension A
+# In/69.pl CJKUnifiedIdeographsExtensionA
+4E00	9FFF	CJK Unified Ideographs
+# In/70.pl CJKUnifiedIdeographs
+A000	A48F	Yi Syllables
+# In/71.pl YiSyllables
+A490	A4CF	Yi Radicals
+# In/72.pl YiRadicals
+AC00	D7A3	Hangul Syllables
+# In/73.pl HangulSyllables
+D800	DB7F	High Surrogates
+# In/74.pl HighSurrogates
+DB80	DBFF	High Private Use Surrogates
+# In/75.pl HighPrivateUseSurrogates
+DC00	DFFF	Low Surrogates
+# In/76.pl LowSurrogates
+E000	F8FF	Private Use
+# In/77.pl PrivateUse
+F900	FAFF	CJK Compatibility Ideographs
+# In/78.pl CJKCompatibilityIdeographs
+FB00	FB4F	Alphabetic Presentation Forms
+# In/79.pl AlphabeticPresentationForms
+FB50	FDFF	Arabic Presentation Forms-A
+# In/80.pl ArabicPresentationFormsA
+FE20	FE2F	Combining Half Marks
+# In/81.pl CombiningHalfMarks
+FE30	FE4F	CJK Compatibility Forms
+# In/82.pl CJKCompatibilityForms
+FE50	FE6F	Small Form Variants
+# In/83.pl SmallFormVariants
+FE70	FEFE	Arabic Presentation Forms-B
+# In/84.pl ArabicPresentationFormsB
+FEFF	FEFF	Specials
+# In/85.pl Specials
+FF00	FFEF	Halfwidth and Fullwidth Forms
+# In/86.pl HalfwidthandFullwidthForms
+FFF0	FFFD	Specials
+# In/85.pl Specials
+10300	1032F	Old Italic
+# In/87.pl OldItalic
+10330	1034F	Gothic
+# In/88.pl Gothic
+10400	1044F	Deseret
+# In/89.pl Deseret
+1D000	1D0FF	Byzantine Musical Symbols
+# In/90.pl ByzantineMusicalSymbols
+1D100	1D1FF	Musical Symbols
+# In/91.pl MusicalSymbols
+1D400	1D7FF	Mathematical Alphanumeric Symbols
+# In/92.pl MathematicalAlphanumericSymbols
+20000	2A6D6	CJK Unified Ideographs Extension B
+# In/93.pl CJKUnifiedIdeographsExtensionB
+2F800	2FA1F	CJK Compatibility Ideographs Supplement
+# In/94.pl CJKCompatibilityIdeographsSupplement
+E0000	E007F	Tags
+# In/95.pl Tags
+F0000	FFFFD	Private Use
+# In/77.pl PrivateUse
+100000	10FFFD	Private Use
+# In/77.pl PrivateUse
+END
diff --git a/lib/unicode/In.pl b/lib/unicode/In.pl
new file mode 100644
index 0000000000..e0b7a5a5f8
--- /dev/null
+++ b/lib/unicode/In.pl
@@ -0,0 +1,101 @@
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by mktables.PL from e.g. Unicode.txt.
+# Any changes made here will be lost!
+%utf8::In = (
+'BasicLatin'                            =>   0,
+'Latin1Supplement'                      =>   1,
+'LatinExtendedA'                        =>   2,
+'LatinExtendedB'                        =>   3,
+'IPAExtensions'                         =>   4,
+'SpacingModifierLetters'                =>   5,
+'CombiningDiacriticalMarks'             =>   6,
+'Greek'                                 =>   7,
+'Cyrillic'                              =>   8,
+'Armenian'                              =>   9,
+'Hebrew'                                =>  10,
+'Arabic'                                =>  11,
+'Syriac'                                =>  12,
+'Thaana'                                =>  13,
+'Devanagari'                            =>  14,
+'Bengali'                               =>  15,
+'Gurmukhi'                              =>  16,
+'Gujarati'                              =>  17,
+'Oriya'                                 =>  18,
+'Tamil'                                 =>  19,
+'Telugu'                                =>  20,
+'Kannada'                               =>  21,
+'Malayalam'                             =>  22,
+'Sinhala'                               =>  23,
+'Thai'                                  =>  24,
+'Lao'                                   =>  25,
+'Tibetan'                               =>  26,
+'Myanmar'                               =>  27,
+'Georgian'                              =>  28,
+'HangulJamo'                            =>  29,
+'Ethiopic'                              =>  30,
+'Cherokee'                              =>  31,
+'UnifiedCanadianAboriginalSyllabics'    =>  32,
+'Ogham'                                 =>  33,
+'Runic'                                 =>  34,
+'Khmer'                                 =>  35,
+'Mongolian'                             =>  36,
+'LatinExtendedAdditional'               =>  37,
+'GreekExtended'                         =>  38,
+'GeneralPunctuation'                    =>  39,
+'SuperscriptsandSubscripts'             =>  40,
+'CurrencySymbols'                       =>  41,
+'CombiningMarksforSymbols'              =>  42,
+'LetterlikeSymbols'                     =>  43,
+'NumberForms'                           =>  44,
+'Arrows'                                =>  45,
+'MathematicalOperators'                 =>  46,
+'MiscellaneousTechnical'                =>  47,
+'ControlPictures'                       =>  48,
+'OpticalCharacterRecognition'           =>  49,
+'EnclosedAlphanumerics'                 =>  50,
+'BoxDrawing'                            =>  51,
+'BlockElements'                         =>  52,
+'GeometricShapes'                       =>  53,
+'MiscellaneousSymbols'                  =>  54,
+'Dingbats'                              =>  55,
+'BraillePatterns'                       =>  56,
+'CJKRadicalsSupplement'                 =>  57,
+'KangxiRadicals'                        =>  58,
+'IdeographicDescriptionCharacters'      =>  59,
+'CJKSymbolsandPunctuation'              =>  60,
+'Hiragana'                              =>  61,
+'Katakana'                              =>  62,
+'Bopomofo'                              =>  63,
+'HangulCompatibilityJamo'               =>  64,
+'Kanbun'                                =>  65,
+'BopomofoExtended'                      =>  66,
+'EnclosedCJKLettersandMonths'           =>  67,
+'CJKCompatibility'                      =>  68,
+'CJKUnifiedIdeographsExtensionA'        =>  69,
+'CJKUnifiedIdeographs'                  =>  70,
+'YiSyllables'                           =>  71,
+'YiRadicals'                            =>  72,
+'HangulSyllables'                       =>  73,
+'HighSurrogates'                        =>  74,
+'HighPrivateUseSurrogates'              =>  75,
+'LowSurrogates'                         =>  76,
+'PrivateUse'                            =>  77,
+'CJKCompatibilityIdeographs'            =>  78,
+'AlphabeticPresentationForms'           =>  79,
+'ArabicPresentationFormsA'              =>  80,
+'CombiningHalfMarks'                    =>  81,
+'CJKCompatibilityForms'                 =>  82,
+'SmallFormVariants'                     =>  83,
+'ArabicPresentationFormsB'              =>  84,
+'Specials'                              =>  85,
+'HalfwidthandFullwidthForms'            =>  86,
+'OldItalic'                             =>  87,
+'Gothic'                                =>  88,
+'Deseret'                               =>  89,
+'ByzantineMusicalSymbols'               =>  90,
+'MusicalSymbols'                        =>  91,
+'MathematicalAlphanumericSymbols'       =>  92,
+'CJKUnifiedIdeographsExtensionB'        =>  93,
+'CJKCompatibilityIdeographsSupplement'  =>  94,
+'Tags'                                  =>  95,
+);
diff --git a/lib/unicode/In/BasicLatin.pl b/lib/unicode/In/0.pl
index 475c1dfed0..475c1dfed0 100644
--- a/lib/unicode/In/BasicLatin.pl
+++ b/lib/unicode/In/0.pl
diff --git a/lib/unicode/In/Latin-1Supplement.pl b/lib/unicode/In/1.pl
index 5a5aa0e18c..5a5aa0e18c 100644
--- a/lib/unicode/In/Latin-1Supplement.pl
+++ b/lib/unicode/In/1.pl
diff --git a/lib/unicode/In/Hebrew.pl b/lib/unicode/In/10.pl
index f1d866c049..f1d866c049 100644
--- a/lib/unicode/In/Hebrew.pl
+++ b/lib/unicode/In/10.pl
diff --git a/lib/unicode/In/Arabic.pl b/lib/unicode/In/11.pl
index 7546a743b5..7546a743b5 100644
--- a/lib/unicode/In/Arabic.pl
+++ b/lib/unicode/In/11.pl
diff --git a/lib/unicode/In/Syriac.pl b/lib/unicode/In/12.pl
index e5247ad937..e5247ad937 100644
--- a/lib/unicode/In/Syriac.pl
+++ b/lib/unicode/In/12.pl
diff --git a/lib/unicode/In/Thaana.pl b/lib/unicode/In/13.pl
index 5bda401f7b..5bda401f7b 100644
--- a/lib/unicode/In/Thaana.pl
+++ b/lib/unicode/In/13.pl
diff --git a/lib/unicode/In/Devanagari.pl b/lib/unicode/In/14.pl
index a20b68d031..a20b68d031 100644
--- a/lib/unicode/In/Devanagari.pl
+++ b/lib/unicode/In/14.pl
diff --git a/lib/unicode/In/Bengali.pl b/lib/unicode/In/15.pl
index 306f653dbc..306f653dbc 100644
--- a/lib/unicode/In/Bengali.pl
+++ b/lib/unicode/In/15.pl
diff --git a/lib/unicode/In/Gurmukhi.pl b/lib/unicode/In/16.pl
index d37d4849ca..d37d4849ca 100644
--- a/lib/unicode/In/Gurmukhi.pl
+++ b/lib/unicode/In/16.pl
diff --git a/lib/unicode/In/Gujarati.pl b/lib/unicode/In/17.pl
index 65d853b314..65d853b314 100644
--- a/lib/unicode/In/Gujarati.pl
+++ b/lib/unicode/In/17.pl
diff --git a/lib/unicode/In/Oriya.pl b/lib/unicode/In/18.pl
index 14e1027fb6..14e1027fb6 100644
--- a/lib/unicode/In/Oriya.pl
+++ b/lib/unicode/In/18.pl
diff --git a/lib/unicode/In/Tamil.pl b/lib/unicode/In/19.pl
index a28ba3d909..a28ba3d909 100644
--- a/lib/unicode/In/Tamil.pl
+++ b/lib/unicode/In/19.pl
diff --git a/lib/unicode/In/LatinExtended-A.pl b/lib/unicode/In/2.pl
index 0f6acf9853..0f6acf9853 100644
--- a/lib/unicode/In/LatinExtended-A.pl
+++ b/lib/unicode/In/2.pl
diff --git a/lib/unicode/In/Telugu.pl b/lib/unicode/In/20.pl
index aff6cc93f4..aff6cc93f4 100644
--- a/lib/unicode/In/Telugu.pl
+++ b/lib/unicode/In/20.pl
diff --git a/lib/unicode/In/Kannada.pl b/lib/unicode/In/21.pl
index 41e05bdc3b..41e05bdc3b 100644
--- a/lib/unicode/In/Kannada.pl
+++ b/lib/unicode/In/21.pl
diff --git a/lib/unicode/In/Malayalam.pl b/lib/unicode/In/22.pl
index b42bbeea8d..b42bbeea8d 100644
--- a/lib/unicode/In/Malayalam.pl
+++ b/lib/unicode/In/22.pl
diff --git a/lib/unicode/In/Sinhala.pl b/lib/unicode/In/23.pl
index 00da6d144f..00da6d144f 100644
--- a/lib/unicode/In/Sinhala.pl
+++ b/lib/unicode/In/23.pl
diff --git a/lib/unicode/In/Thai.pl b/lib/unicode/In/24.pl
index 2fa00eb135..2fa00eb135 100644
--- a/lib/unicode/In/Thai.pl
+++ b/lib/unicode/In/24.pl
diff --git a/lib/unicode/In/Lao.pl b/lib/unicode/In/25.pl
index 5fd607c08f..5fd607c08f 100644
--- a/lib/unicode/In/Lao.pl
+++ b/lib/unicode/In/25.pl
diff --git a/lib/unicode/In/Tibetan.pl b/lib/unicode/In/26.pl
index 3ae5e6248d..3ae5e6248d 100644
--- a/lib/unicode/In/Tibetan.pl
+++ b/lib/unicode/In/26.pl
diff --git a/lib/unicode/In/Myanmar.pl b/lib/unicode/In/27.pl
index ecc3448361..ecc3448361 100644
--- a/lib/unicode/In/Myanmar.pl
+++ b/lib/unicode/In/27.pl
diff --git a/lib/unicode/In/Georgian.pl b/lib/unicode/In/28.pl
index 73a8818c71..73a8818c71 100644
--- a/lib/unicode/In/Georgian.pl
+++ b/lib/unicode/In/28.pl
diff --git a/lib/unicode/In/HangulJamo.pl b/lib/unicode/In/29.pl
index 692be7d813..692be7d813 100644
--- a/lib/unicode/In/HangulJamo.pl
+++ b/lib/unicode/In/29.pl
diff --git a/lib/unicode/In/LatinExtended-B.pl b/lib/unicode/In/3.pl
index 68f093234e..68f093234e 100644
--- a/lib/unicode/In/LatinExtended-B.pl
+++ b/lib/unicode/In/3.pl
diff --git a/lib/unicode/In/Ethiopic.pl b/lib/unicode/In/30.pl
index ad4776df99..ad4776df99 100644
--- a/lib/unicode/In/Ethiopic.pl
+++ b/lib/unicode/In/30.pl
diff --git a/lib/unicode/In/Cherokee.pl b/lib/unicode/In/31.pl
index f40dfa2be0..f40dfa2be0 100644
--- a/lib/unicode/In/Cherokee.pl
+++ b/lib/unicode/In/31.pl
diff --git a/lib/unicode/In/UnifiedCanadianAboriginalSyllabics.pl b/lib/unicode/In/32.pl
index 7318008076..7318008076 100644
--- a/lib/unicode/In/UnifiedCanadianAboriginalSyllabics.pl
+++ b/lib/unicode/In/32.pl
diff --git a/lib/unicode/In/Ogham.pl b/lib/unicode/In/33.pl
index 5d7bd970e8..5d7bd970e8 100644
--- a/lib/unicode/In/Ogham.pl
+++ b/lib/unicode/In/33.pl
diff --git a/lib/unicode/In/Runic.pl b/lib/unicode/In/34.pl
index d404cb6cfb..d404cb6cfb 100644
--- a/lib/unicode/In/Runic.pl
+++ b/lib/unicode/In/34.pl
diff --git a/lib/unicode/In/Khmer.pl b/lib/unicode/In/35.pl
index 2b0b198216..2b0b198216 100644
--- a/lib/unicode/In/Khmer.pl
+++ b/lib/unicode/In/35.pl
diff --git a/lib/unicode/In/Mongolian.pl b/lib/unicode/In/36.pl
index 06526c64d9..06526c64d9 100644
--- a/lib/unicode/In/Mongolian.pl
+++ b/lib/unicode/In/36.pl
diff --git a/lib/unicode/In/LatinExtendedAdditional.pl b/lib/unicode/In/37.pl
index c288810ca2..c288810ca2 100644
--- a/lib/unicode/In/LatinExtendedAdditional.pl
+++ b/lib/unicode/In/37.pl
diff --git a/lib/unicode/In/GreekExtended.pl b/lib/unicode/In/38.pl
index 74cd2c88e0..74cd2c88e0 100644
--- a/lib/unicode/In/GreekExtended.pl
+++ b/lib/unicode/In/38.pl
diff --git a/lib/unicode/In/GeneralPunctuation.pl b/lib/unicode/In/39.pl
index b9b0e7efaa..b9b0e7efaa 100644
--- a/lib/unicode/In/GeneralPunctuation.pl
+++ b/lib/unicode/In/39.pl
diff --git a/lib/unicode/In/IPAExtensions.pl b/lib/unicode/In/4.pl
index f6e9454fe0..f6e9454fe0 100644
--- a/lib/unicode/In/IPAExtensions.pl
+++ b/lib/unicode/In/4.pl
diff --git a/lib/unicode/In/SuperscriptsandSubscripts.pl b/lib/unicode/In/40.pl
index 2e36ac331c..2e36ac331c 100644
--- a/lib/unicode/In/SuperscriptsandSubscripts.pl
+++ b/lib/unicode/In/40.pl
diff --git a/lib/unicode/In/CurrencySymbols.pl b/lib/unicode/In/41.pl
index 12c67371cc..12c67371cc 100644
--- a/lib/unicode/In/CurrencySymbols.pl
+++ b/lib/unicode/In/41.pl
diff --git a/lib/unicode/In/CombiningMarksforSymbols.pl b/lib/unicode/In/42.pl
index 2d58a56712..2d58a56712 100644
--- a/lib/unicode/In/CombiningMarksforSymbols.pl
+++ b/lib/unicode/In/42.pl
diff --git a/lib/unicode/In/LetterlikeSymbols.pl b/lib/unicode/In/43.pl
index c735821edc..c735821edc 100644
--- a/lib/unicode/In/LetterlikeSymbols.pl
+++ b/lib/unicode/In/43.pl
diff --git a/lib/unicode/In/NumberForms.pl b/lib/unicode/In/44.pl
index a1949a194d..a1949a194d 100644
--- a/lib/unicode/In/NumberForms.pl
+++ b/lib/unicode/In/44.pl
diff --git a/lib/unicode/In/Arrows.pl b/lib/unicode/In/45.pl
index 799f739085..799f739085 100644
--- a/lib/unicode/In/Arrows.pl
+++ b/lib/unicode/In/45.pl
diff --git a/lib/unicode/In/MathematicalOperators.pl b/lib/unicode/In/46.pl
index 8bc8295cc5..8bc8295cc5 100644
--- a/lib/unicode/In/MathematicalOperators.pl
+++ b/lib/unicode/In/46.pl
diff --git a/lib/unicode/In/MiscellaneousTechnical.pl b/lib/unicode/In/47.pl
index 67867951d6..67867951d6 100644
--- a/lib/unicode/In/MiscellaneousTechnical.pl
+++ b/lib/unicode/In/47.pl
diff --git a/lib/unicode/In/ControlPictures.pl b/lib/unicode/In/48.pl
index 7aad2fcacf..7aad2fcacf 100644
--- a/lib/unicode/In/ControlPictures.pl
+++ b/lib/unicode/In/48.pl
diff --git a/lib/unicode/In/OpticalCharacterRecognition.pl b/lib/unicode/In/49.pl
index c7cecd02da..c7cecd02da 100644
--- a/lib/unicode/In/OpticalCharacterRecognition.pl
+++ b/lib/unicode/In/49.pl
diff --git a/lib/unicode/In/SpacingModifierLetters.pl b/lib/unicode/In/5.pl
index a242e0207a..a242e0207a 100644
--- a/lib/unicode/In/SpacingModifierLetters.pl
+++ b/lib/unicode/In/5.pl
diff --git a/lib/unicode/In/EnclosedAlphanumerics.pl b/lib/unicode/In/50.pl
index 7b1b778af0..7b1b778af0 100644
--- a/lib/unicode/In/EnclosedAlphanumerics.pl
+++ b/lib/unicode/In/50.pl
diff --git a/lib/unicode/In/BoxDrawing.pl b/lib/unicode/In/51.pl
index 4d446863fe..4d446863fe 100644
--- a/lib/unicode/In/BoxDrawing.pl
+++ b/lib/unicode/In/51.pl
diff --git a/lib/unicode/In/BlockElements.pl b/lib/unicode/In/52.pl
index 6135c93e90..6135c93e90 100644
--- a/lib/unicode/In/BlockElements.pl
+++ b/lib/unicode/In/52.pl
diff --git a/lib/unicode/In/GeometricShapes.pl b/lib/unicode/In/53.pl
index 855d98ebff..855d98ebff 100644
--- a/lib/unicode/In/GeometricShapes.pl
+++ b/lib/unicode/In/53.pl
diff --git a/lib/unicode/In/MiscellaneousSymbols.pl b/lib/unicode/In/54.pl
index 0949bc2b55..0949bc2b55 100644
--- a/lib/unicode/In/MiscellaneousSymbols.pl
+++ b/lib/unicode/In/54.pl
diff --git a/lib/unicode/In/Dingbats.pl b/lib/unicode/In/55.pl
index 3013f73c75..3013f73c75 100644
--- a/lib/unicode/In/Dingbats.pl
+++ b/lib/unicode/In/55.pl
diff --git a/lib/unicode/In/BraillePatterns.pl b/lib/unicode/In/56.pl
index d785c31676..d785c31676 100644
--- a/lib/unicode/In/BraillePatterns.pl
+++ b/lib/unicode/In/56.pl
diff --git a/lib/unicode/In/CJKRadicalsSupplement.pl b/lib/unicode/In/57.pl
index 2bf56517d1..2bf56517d1 100644
--- a/lib/unicode/In/CJKRadicalsSupplement.pl
+++ b/lib/unicode/In/57.pl
diff --git a/lib/unicode/In/KangxiRadicals.pl b/lib/unicode/In/58.pl
index 3903f15c4c..3903f15c4c 100644
--- a/lib/unicode/In/KangxiRadicals.pl
+++ b/lib/unicode/In/58.pl
diff --git a/lib/unicode/In/IdeographicDescriptionCharacters.pl b/lib/unicode/In/59.pl
index 07799e6941..07799e6941 100644
--- a/lib/unicode/In/IdeographicDescriptionCharacters.pl
+++ b/lib/unicode/In/59.pl
diff --git a/lib/unicode/In/CombiningDiacriticalMarks.pl b/lib/unicode/In/6.pl
index cf9bb94991..cf9bb94991 100644
--- a/lib/unicode/In/CombiningDiacriticalMarks.pl
+++ b/lib/unicode/In/6.pl
diff --git a/lib/unicode/In/CJKSymbolsandPunctuation.pl b/lib/unicode/In/60.pl
index 0c66f051a4..0c66f051a4 100644
--- a/lib/unicode/In/CJKSymbolsandPunctuation.pl
+++ b/lib/unicode/In/60.pl
diff --git a/lib/unicode/In/Hiragana.pl b/lib/unicode/In/61.pl
index 49b4e4976a..49b4e4976a 100644
--- a/lib/unicode/In/Hiragana.pl
+++ b/lib/unicode/In/61.pl
diff --git a/lib/unicode/In/Katakana.pl b/lib/unicode/In/62.pl
index e5568a283a..e5568a283a 100644
--- a/lib/unicode/In/Katakana.pl
+++ b/lib/unicode/In/62.pl
diff --git a/lib/unicode/In/Bopomofo.pl b/lib/unicode/In/63.pl
index 4f9b5f46b2..4f9b5f46b2 100644
--- a/lib/unicode/In/Bopomofo.pl
+++ b/lib/unicode/In/63.pl
diff --git a/lib/unicode/In/HangulCompatibilityJamo.pl b/lib/unicode/In/64.pl
index b15c4cc760..b15c4cc760 100644
--- a/lib/unicode/In/HangulCompatibilityJamo.pl
+++ b/lib/unicode/In/64.pl
diff --git a/lib/unicode/In/Kanbun.pl b/lib/unicode/In/65.pl
index d78c2088c0..d78c2088c0 100644
--- a/lib/unicode/In/Kanbun.pl
+++ b/lib/unicode/In/65.pl
diff --git a/lib/unicode/In/BopomofoExtended.pl b/lib/unicode/In/66.pl
index 96150b4f3f..96150b4f3f 100644
--- a/lib/unicode/In/BopomofoExtended.pl
+++ b/lib/unicode/In/66.pl
diff --git a/lib/unicode/In/EnclosedCJKLettersandMonths.pl b/lib/unicode/In/67.pl
index 2708fec7e3..2708fec7e3 100644
--- a/lib/unicode/In/EnclosedCJKLettersandMonths.pl
+++ b/lib/unicode/In/67.pl
diff --git a/lib/unicode/In/CJKCompatibility.pl b/lib/unicode/In/68.pl
index d504529398..d504529398 100644
--- a/lib/unicode/In/CJKCompatibility.pl
+++ b/lib/unicode/In/68.pl
diff --git a/lib/unicode/In/CJKUnifiedIdeographsExtensionA.pl b/lib/unicode/In/69.pl
index 83adb815d7..83adb815d7 100644
--- a/lib/unicode/In/CJKUnifiedIdeographsExtensionA.pl
+++ b/lib/unicode/In/69.pl
diff --git a/lib/unicode/In/Greek.pl b/lib/unicode/In/7.pl
index 8d89b7176b..8d89b7176b 100644
--- a/lib/unicode/In/Greek.pl
+++ b/lib/unicode/In/7.pl
diff --git a/lib/unicode/In/CJKUnifiedIdeographs.pl b/lib/unicode/In/70.pl
index f74552e661..f74552e661 100644
--- a/lib/unicode/In/CJKUnifiedIdeographs.pl
+++ b/lib/unicode/In/70.pl
diff --git a/lib/unicode/In/YiSyllables.pl b/lib/unicode/In/71.pl
index 0636a82e56..0636a82e56 100644
--- a/lib/unicode/In/YiSyllables.pl
+++ b/lib/unicode/In/71.pl
diff --git a/lib/unicode/In/YiRadicals.pl b/lib/unicode/In/72.pl
index 56404c5fb5..56404c5fb5 100644
--- a/lib/unicode/In/YiRadicals.pl
+++ b/lib/unicode/In/72.pl
diff --git a/lib/unicode/In/HangulSyllables.pl b/lib/unicode/In/73.pl
index e1e26945e5..e1e26945e5 100644
--- a/lib/unicode/In/HangulSyllables.pl
+++ b/lib/unicode/In/73.pl
diff --git a/lib/unicode/In/HighSurrogates.pl b/lib/unicode/In/74.pl
index 0f4eb5727b..0f4eb5727b 100644
--- a/lib/unicode/In/HighSurrogates.pl
+++ b/lib/unicode/In/74.pl
diff --git a/lib/unicode/In/HighPrivateUseSurrogates.pl b/lib/unicode/In/75.pl
index ec4ca07885..ec4ca07885 100644
--- a/lib/unicode/In/HighPrivateUseSurrogates.pl
+++ b/lib/unicode/In/75.pl
diff --git a/lib/unicode/In/LowSurrogates.pl b/lib/unicode/In/76.pl
index d056168c66..d056168c66 100644
--- a/lib/unicode/In/LowSurrogates.pl
+++ b/lib/unicode/In/76.pl
diff --git a/lib/unicode/In/77.pl b/lib/unicode/In/77.pl
new file mode 100644
index 0000000000..530166da95
--- /dev/null
+++ b/lib/unicode/In/77.pl
@@ -0,0 +1,6 @@
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by mktables.PL from e.g. Unicode.txt.
+# Any changes made here will be lost!
+return <<'END';
+100000	10FFFD
+END
diff --git a/lib/unicode/In/CJKCompatibilityIdeographs.pl b/lib/unicode/In/78.pl
index 0c553d6ee2..0c553d6ee2 100644
--- a/lib/unicode/In/CJKCompatibilityIdeographs.pl
+++ b/lib/unicode/In/78.pl
diff --git a/lib/unicode/In/AlphabeticPresentationForms.pl b/lib/unicode/In/79.pl
index 42cc1ca029..42cc1ca029 100644
--- a/lib/unicode/In/AlphabeticPresentationForms.pl
+++ b/lib/unicode/In/79.pl
diff --git a/lib/unicode/In/Cyrillic.pl b/lib/unicode/In/8.pl
index 0075ce1ddf..0075ce1ddf 100644
--- a/lib/unicode/In/Cyrillic.pl
+++ b/lib/unicode/In/8.pl
diff --git a/lib/unicode/In/ArabicPresentationForms-A.pl b/lib/unicode/In/80.pl
index ffb4f1eb3a..ffb4f1eb3a 100644
--- a/lib/unicode/In/ArabicPresentationForms-A.pl
+++ b/lib/unicode/In/80.pl
diff --git a/lib/unicode/In/CombiningHalfMarks.pl b/lib/unicode/In/81.pl
index cc8a4a21b1..cc8a4a21b1 100644
--- a/lib/unicode/In/CombiningHalfMarks.pl
+++ b/lib/unicode/In/81.pl
diff --git a/lib/unicode/In/CJKCompatibilityForms.pl b/lib/unicode/In/82.pl
index 4e462b8402..4e462b8402 100644
--- a/lib/unicode/In/CJKCompatibilityForms.pl
+++ b/lib/unicode/In/82.pl
diff --git a/lib/unicode/In/SmallFormVariants.pl b/lib/unicode/In/83.pl
index 4eff1ea01e..4eff1ea01e 100644
--- a/lib/unicode/In/SmallFormVariants.pl
+++ b/lib/unicode/In/83.pl
diff --git a/lib/unicode/In/ArabicPresentationForms-B.pl b/lib/unicode/In/84.pl
index dc5a32e4b1..dc5a32e4b1 100644
--- a/lib/unicode/In/ArabicPresentationForms-B.pl
+++ b/lib/unicode/In/84.pl
diff --git a/lib/unicode/In/Specials.pl b/lib/unicode/In/85.pl
index 931fc5b902..931fc5b902 100644
--- a/lib/unicode/In/Specials.pl
+++ b/lib/unicode/In/85.pl
diff --git a/lib/unicode/In/HalfwidthandFullwidthForms.pl b/lib/unicode/In/86.pl
index 03e85154fb..03e85154fb 100644
--- a/lib/unicode/In/HalfwidthandFullwidthForms.pl
+++ b/lib/unicode/In/86.pl
diff --git a/lib/unicode/Block.pl b/lib/unicode/In/87.pl
index 272f63fc9f..44a5e47510 100644
--- a/lib/unicode/Block.pl
+++ b/lib/unicode/In/87.pl
@@ -2,4 +2,5 @@
 # This file is built by mktables.PL from e.g. Unicode.txt.
 # Any changes made here will be lost!
 return <<'END';
+10300	1032F
 END
diff --git a/lib/unicode/In/88.pl b/lib/unicode/In/88.pl
new file mode 100644
index 0000000000..803041101c
--- /dev/null
+++ b/lib/unicode/In/88.pl
@@ -0,0 +1,6 @@
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by mktables.PL from e.g. Unicode.txt.
+# Any changes made here will be lost!
+return <<'END';
+10330	1034F
+END
diff --git a/lib/unicode/In/89.pl b/lib/unicode/In/89.pl
new file mode 100644
index 0000000000..d2c50bbcad
--- /dev/null
+++ b/lib/unicode/In/89.pl
@@ -0,0 +1,6 @@
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by mktables.PL from e.g. Unicode.txt.
+# Any changes made here will be lost!
+return <<'END';
+10400	1044F
+END
diff --git a/lib/unicode/In/Armenian.pl b/lib/unicode/In/9.pl
index a6d50e3be5..a6d50e3be5 100644
--- a/lib/unicode/In/Armenian.pl
+++ b/lib/unicode/In/9.pl
diff --git a/lib/unicode/In/90.pl b/lib/unicode/In/90.pl
new file mode 100644
index 0000000000..f1073c7392
--- /dev/null
+++ b/lib/unicode/In/90.pl
@@ -0,0 +1,6 @@
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by mktables.PL from e.g. Unicode.txt.
+# Any changes made here will be lost!
+return <<'END';
+1D000	1D0FF
+END
diff --git a/lib/unicode/In/91.pl b/lib/unicode/In/91.pl
new file mode 100644
index 0000000000..7435889d7c
--- /dev/null
+++ b/lib/unicode/In/91.pl
@@ -0,0 +1,6 @@
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by mktables.PL from e.g. Unicode.txt.
+# Any changes made here will be lost!
+return <<'END';
+1D100	1D1FF
+END
diff --git a/lib/unicode/In/92.pl b/lib/unicode/In/92.pl
new file mode 100644
index 0000000000..7e40edc3ed
--- /dev/null
+++ b/lib/unicode/In/92.pl
@@ -0,0 +1,6 @@
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by mktables.PL from e.g. Unicode.txt.
+# Any changes made here will be lost!
+return <<'END';
+1D400	1D7FF
+END
diff --git a/lib/unicode/In/93.pl b/lib/unicode/In/93.pl
new file mode 100644
index 0000000000..931aec3891
--- /dev/null
+++ b/lib/unicode/In/93.pl
@@ -0,0 +1,6 @@
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by mktables.PL from e.g. Unicode.txt.
+# Any changes made here will be lost!
+return <<'END';
+20000	2A6D6
+END
diff --git a/lib/unicode/In/94.pl b/lib/unicode/In/94.pl
new file mode 100644
index 0000000000..c025148c04
--- /dev/null
+++ b/lib/unicode/In/94.pl
@@ -0,0 +1,6 @@
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by mktables.PL from e.g. Unicode.txt.
+# Any changes made here will be lost!
+return <<'END';
+2F800	2FA1F
+END
diff --git a/lib/unicode/In/95.pl b/lib/unicode/In/95.pl
new file mode 100644
index 0000000000..495d2d581d
--- /dev/null
+++ b/lib/unicode/In/95.pl
@@ -0,0 +1,6 @@
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by mktables.PL from e.g. Unicode.txt.
+# Any changes made here will be lost!
+return <<'END';
+E0000	E007F
+END
diff --git a/lib/unicode/In/PrivateUse.pl b/lib/unicode/In/PrivateUse.pl
deleted file mode 100644
index c81b567a74..0000000000
--- a/lib/unicode/In/PrivateUse.pl
+++ /dev/null
@@ -1,6 +0,0 @@
-# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
-# This file is built by mktables.PL from e.g. Unicode.txt.
-# Any changes made here will be lost!
-return <<'END';
-E000	F8FF
-END
diff --git a/lib/unicode/mktables.PL b/lib/unicode/mktables.PL
index 818785452b..637050a3fc 100755
--- a/lib/unicode/mktables.PL
+++ b/lib/unicode/mktables.PL
@@ -231,11 +231,24 @@ mkdir "To", 0755;
 
 # This is not written for speed...
 
+my %InId;
+my $InId = 0;
+
 foreach $file (@todo) {
     my ($table, $wanted, $val) = @$file;
     next if @ARGV and not grep { $_ eq $table } @ARGV;
-    print $table,"\n";
-    if ($table =~ /^(Is|In|To)(.*)/) {
+    print $table, "\n";
+    $table =~ s/\W+//g;
+    if ($table =~ /^In(.+)/) {
+	my $id;
+        unless (exists $InId{$1}) {
+	    $InId{$1} = $InId++;
+	}
+	$id = $InId{$1};
+	open(OUT, ">In/$id.pl") or die "Can't create In/$id.pl: $!\n";
+	print OUT "# In/$id.pl $1\n";
+    }
+    elsif ($table =~ /^(Is|To)(.+)/) {
 	open(OUT, ">$1/$2.pl") or die "Can't create $1/$2.pl: $!\n";
     }
     else {
@@ -257,9 +270,9 @@ END
 # Must treat blocks specially.
 
 exit if @ARGV and not grep { $_ eq Block } @ARGV;
-print "Block\n";
+print "Blocks\n";
 open(UD, 'Blocks.txt') or die "Can't open Blocks.txt: $!\n";
-open(OUT, ">Block.pl") or die "Can't create Block.pl: $!\n";
+open(OUT, ">Blocks.pl") or die "Can't create Blocks.pl: $!\n";
 print OUT <<EOH;
 # !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
 # This file is built by $0 from e.g. $UnicodeData.
@@ -273,11 +286,17 @@ while (<UD>) {
     next if /^#/;
     next if /^$/;
     chomp;
-    ($code, $last, $name) = /^([0-9a-f]+)\.\.([0-9a-f]); (.+)/i;
+    ($code, $last, $name) = /^([0-9a-f]+)\.\.([0-9a-f]+); (.+)/i;
     if ($name) {
 	print OUT "$code	$last	$name\n";
-	$name =~ s/\s+//g;
-	open(BLOCK, ">In/$name.pl");
+	$name =~ s/\W+//g;
+	my $id;
+        unless (exists $InId{$name}) {
+	    $InId{$name} = $InId++;
+	}
+	$id = $InId{$name};
+	open(BLOCK, ">In/$id.pl");
+	print OUT "# In/$id.pl $name\n";
 	print BLOCK <<EOH;
 # !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
 # This file is built by $0 from e.g. $UnicodeData.
@@ -295,6 +314,24 @@ END2
 print OUT "END\n";
 close OUT;
 
+open(INID, ">In.pl");
+
+print INID <<EOH;
+# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!! 
+# This file is built by $0 from e.g. $UnicodeData.
+# Any changes made here will be lost!
+%utf8::In = (
+EOH
+
+# Order doesn't matter but let's prettyprint anyway.
+foreach my $in (sort { $InId{$a} <=> $InId{$b} } keys %InId) {
+    printf INID "%-40s => %3d,\n", "'$in'", $InId{$in};
+}
+
+print INID ");\n";
+
+close(INID);
+
 ##################################################
 
 sub proplist {
diff --git a/lib/utf8_heavy.pl b/lib/utf8_heavy.pl
index 8649e9e07e..ab2e15ddec 100644
--- a/lib/utf8_heavy.pl
+++ b/lib/utf8_heavy.pl
@@ -26,12 +26,19 @@ sub SWASHNEW {
     while (($caller = caller($i)) eq __PACKAGE__) { $i++ }
     my $encoding = $enc{$caller} || "unicode";
     (my $file = $type) =~ s!::!/!g;
-    $file =~ s#^(I[sn]|To)([A-Z].*)#$1/$2#;
+    if ($file =~ /^In(.+)/) {
+	defined %utf8::In || do "$encoding/In.pl";
+	if (exists $utf8::In{$1}) {
+	    $file = "$enconding/In/$utf8::In{$1}";
+	}
+    } else {
+	$file =~ s#^(Is|To)([A-Z].*)#$1/$2#;
+    }
     $list ||= eval { $caller->$type(); }
 	|| do "$file.pl"
 	|| do "$encoding/$file.pl"
 	|| do "$encoding/Is/${type}.pl"
-	|| croak("Can't find $encoding character property definition via $caller->$type or $file.pl");
+	|| croak("Can't find $encoding character property \"$type\"");
 
     $| = 1;
 
diff --git a/objXSUB.h b/objXSUB.h
index 99d9a3ea26..28bed782f5 100644
--- a/objXSUB.h
+++ b/objXSUB.h
@@ -579,6 +579,10 @@
 #define Perl_init_stacks	pPerl->Perl_init_stacks
 #undef  init_stacks
 #define init_stacks		Perl_init_stacks
+#undef  Perl_init_tm
+#define Perl_init_tm		pPerl->Perl_init_tm
+#undef  init_tm
+#define init_tm			Perl_init_tm
 #undef  Perl_instr
 #define Perl_instr		pPerl->Perl_instr
 #undef  instr
@@ -857,6 +861,10 @@
 #define Perl_mg_size		pPerl->Perl_mg_size
 #undef  mg_size
 #define mg_size			Perl_mg_size
+#undef  Perl_mini_mktime
+#define Perl_mini_mktime	pPerl->Perl_mini_mktime
+#undef  mini_mktime
+#define mini_mktime		Perl_mini_mktime
 #undef  Perl_moreswitches
 #define Perl_moreswitches	pPerl->Perl_moreswitches
 #undef  moreswitches
@@ -927,6 +935,10 @@
 #define Perl_my_stat		pPerl->Perl_my_stat
 #undef  my_stat
 #define my_stat			Perl_my_stat
+#undef  Perl_my_strftime
+#define Perl_my_strftime	pPerl->Perl_my_strftime
+#undef  my_strftime
+#define my_strftime		Perl_my_strftime
 #if defined(MYSWAP)
 #undef  Perl_my_swap
 #define Perl_my_swap		pPerl->Perl_my_swap
diff --git a/perl.h b/perl.h
index 01a6d3fcb9..57afb3e37c 100644
--- a/perl.h
+++ b/perl.h
@@ -1842,10 +1842,12 @@ typedef pthread_key_t	perl_key;
 #endif
 
 /* This defines a way to flush all output buffers.  This may be a
- * performance issue, so we allow people to disable it.
+ * performance issue, so we allow people to disable it.  Also, if
+ * we are using stdio, there are broken implementations of fflush(NULL)
+ * out there, Solaris being the most prominent.
  */
 #ifndef PERL_FLUSHALL_FOR_CHILD
-# if defined(FFLUSH_NULL) || defined(USE_SFIO)
+# if defined(USE_PERLIO) || defined(FFLUSH_NULL) || defined(USE_SFIO)
 #  define PERL_FLUSHALL_FOR_CHILD	PerlIO_flush((PerlIO*)NULL)
 # else
 #  ifdef FFLUSH_ALL
diff --git a/pod/perldiag.pod b/pod/perldiag.pod
index 6f7ed5fd39..a2614c121e 100644
--- a/pod/perldiag.pod
+++ b/pod/perldiag.pod
@@ -628,6 +628,13 @@ found in the PATH did not have correct permissions.
 (F) A string of a form C<CORE::word> was given to prototype(), but there
 is no builtin with the name C<word>.
 
+=item Can't find %s character property "%s"
+
+(F) You used C<\p{}> or C<\P{}> but the character property by that name
+could not be find.  Maybe you mispelled the name of the property
+(remember that the names of character properties consist only of
+alphanumeric characters), or maybe you forgot the C<Is> or C<In> prefix?
+
 =item Can't find label %s
 
 (F) You said to goto a label that isn't mentioned anywhere that it's
@@ -1707,7 +1714,9 @@ L<perlfunc/sprintf>.
 =item invalid [] range "%s" in regexp
 
 (F) The range specified in a character class had a minimum character
-greater than the maximum character.  See L<perlre>.
+greater than the maximum character.  One possibility is that you
+forgot the C<{}> from your ending C<\x{}> - C<\x> without the curly
+braces can go only up to C<ff>.  See L<perlre>.
 
 =item invalid [] range "%s" in transliteration operator
 
diff --git a/pod/perlunicode.pod b/pod/perlunicode.pod
index 8ddcdd2b06..12bee5c7a3 100644
--- a/pod/perlunicode.pod
+++ b/pod/perlunicode.pod
@@ -158,9 +158,12 @@ Named Unicode properties and block ranges make be used as character
 classes via the new C<\p{}> (matches property) and C<\P{}> (doesn't
 match property) constructs.  For instance, C<\p{Lu}> matches any
 character with the Unicode uppercase property, while C<\p{M}> matches
-any mark character.  Single letter properties may omit the brackets, so
-that can be written C<\pM> also.  Many predefined character classes are
-available, such as C<\p{IsMirrored}> and  C<\p{InTibetan}>.
+any mark character.  Single letter properties may omit the brackets,
+so that can be written C<\pM> also.  Many predefined character classes
+are available, such as C<\p{IsMirrored}> and C<\p{InTibetan}>.  The
+names of the C<In> classes are the official Unicode block names but
+with all non-alphanumeric characters removed, for example the block
+name C<"Latin-1 Supplement"> becomes C<\p{InLatin1Supplement}>.
 
 =item *
 
diff --git a/proto.h b/proto.h
index 63fc5187f2..cc4050d86e 100644
--- a/proto.h
+++ b/proto.h
@@ -808,7 +808,7 @@ PERL_CALLCONV void	Perl_sv_vcatpvfn(pTHX_ SV* sv, const char* pat, STRLEN patlen
 PERL_CALLCONV void	Perl_sv_vsetpvfn(pTHX_ SV* sv, const char* pat, STRLEN patlen, va_list* args, SV** svargs, I32 svmax, bool *maybe_tainted);
 PERL_CALLCONV NV	Perl_str_to_version(pTHX_ SV *sv);
 PERL_CALLCONV SV*	Perl_swash_init(pTHX_ char* pkg, char* name, SV* listsv, I32 minbits, I32 none);
-PERL_CALLCONV UV	Perl_swash_fetch(pTHX_ SV *sv, U8 *ptr);
+PERL_CALLCONV UV	Perl_swash_fetch(pTHX_ SV *sv, U8 *ptr, bool do_utf8);
 PERL_CALLCONV void	Perl_taint_env(pTHX);
 PERL_CALLCONV void	Perl_taint_proper(pTHX_ const char* f, const char* s);
 PERL_CALLCONV UV	Perl_to_utf8_lower(pTHX_ U8 *p);
diff --git a/regcomp.c b/regcomp.c
index 1cc3a984e1..20388f1350 100644
--- a/regcomp.c
+++ b/regcomp.c
@@ -2799,11 +2799,12 @@ tryagain:
 	    break;
 	case 'p':
 	case 'P':
-	    {	/* a lovely hack--pretend we saw [\pX] instead */
+	    {	
 		char* oldregxend = RExC_end;
                 char* parse_start = RExC_parse;
 
 		if (RExC_parse[1] == '{') {
+		  /* a lovely hack--pretend we saw [\pX] instead */
 		    RExC_end = strchr(RExC_parse, '}');
 		    if (!RExC_end) {
 			RExC_parse += 2;
@@ -3259,7 +3260,7 @@ STATIC regnode *
 S_regclass(pTHX_ RExC_state_t *pRExC_state)
 {
     register UV value;
-    register IV lastvalue = OOB_UNICODE;
+    register IV prevvalue = OOB_UNICODE;
     register IV range = 0;
     register regnode *ret;
     STRLEN numlen;
@@ -3270,7 +3271,7 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
     register char *e;
     char *parse_start = RExC_parse; /* MJD */
     UV n;
-    bool dont_optimize_invert = FALSE;
+    bool optimize_invert = TRUE;
 
     ret = reganode(pRExC_state, ANYOF, 0);
 
@@ -3312,8 +3313,8 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 	    rangebegin = RExC_parse;
 	if (UTF) {
 	    value = utf8n_to_uvchr((U8*)RExC_parse,
-			       RExC_end - RExC_parse,
-			       &numlen, 0);
+				   RExC_end - RExC_parse,
+				   &numlen, 0);
 	    RExC_parse += numlen;
 	}
 	else
@@ -3423,14 +3424,14 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			       RExC_parse - rangebegin,
 			       RExC_parse - rangebegin,
 			       rangebegin);
-		    if (lastvalue < 256) {
-			ANYOF_BITMAP_SET(ret, lastvalue);
+		    if (prevvalue < 256) {
+			ANYOF_BITMAP_SET(ret, prevvalue);
 			ANYOF_BITMAP_SET(ret, '-');
 		    }
 		    else {
 			ANYOF_FLAGS(ret) |= ANYOF_UNICODE;
 			Perl_sv_catpvf(aTHX_ listsv,
-				       "%04"UVxf"\n%04"UVxf"\n", (UV)lastvalue, (UV) '-');
+				       "%04"UVxf"\n%04"UVxf"\n", (UV)prevvalue, (UV) '-');
 		    }
 		}
 
@@ -3438,6 +3439,8 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 	    }
 
 	    if (!SIZE_ONLY) {
+	        if (namedclass > OOB_NAMEDCLASS)
+		    optimize_invert = FALSE;
 		/* Possible truncation here but in some 64-bit environments
 		 * the compiler gets heartburn about switch on 64-bit values.
 		 * A similar issue a little earlier when switching on value.
@@ -3451,7 +3454,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isALNUM(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsWord\n");	
 		    break;
 		case ANYOF_NALNUM:
@@ -3462,7 +3464,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isALNUM(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsWord\n");
 		    break;
 		case ANYOF_ALNUMC:
@@ -3473,7 +3474,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isALNUMC(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsAlnum\n");
 		    break;
 		case ANYOF_NALNUMC:
@@ -3484,7 +3484,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isALNUMC(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsAlnum\n");
 		    break;
 		case ANYOF_ALPHA:
@@ -3495,7 +3494,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isALPHA(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsAlpha\n");
 		    break;
 		case ANYOF_NALPHA:
@@ -3506,7 +3504,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isALPHA(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsAlpha\n");
 		    break;
 		case ANYOF_ASCII:
@@ -3529,7 +3526,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			}
 #endif /* EBCDIC */
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsASCII\n");
 		    break;
 		case ANYOF_NASCII:
@@ -3552,7 +3548,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			}
 #endif /* EBCDIC */
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsASCII\n");
 		    break;
 		case ANYOF_BLANK:
@@ -3563,7 +3558,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isBLANK(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsBlank\n");
 		    break;
 		case ANYOF_NBLANK:
@@ -3574,7 +3568,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isBLANK(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsBlank\n");
 		    break;
 		case ANYOF_CNTRL:
@@ -3585,7 +3578,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isCNTRL(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsCntrl\n");
 		    break;
 		case ANYOF_NCNTRL:
@@ -3596,7 +3588,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isCNTRL(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsCntrl\n");
 		    break;
 		case ANYOF_DIGIT:
@@ -3607,7 +3598,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			for (value = '0'; value <= '9'; value++)
 			    ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsDigit\n");
 		    break;
 		case ANYOF_NDIGIT:
@@ -3620,7 +3610,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			for (value = '9' + 1; value < 256; value++)
 			    ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsDigit\n");
 		    break;
 		case ANYOF_GRAPH:
@@ -3631,7 +3620,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isGRAPH(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsGraph\n");
 		    break;
 		case ANYOF_NGRAPH:
@@ -3642,7 +3630,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isGRAPH(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsGraph\n");
 		    break;
 		case ANYOF_LOWER:
@@ -3653,7 +3640,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isLOWER(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsLower\n");
 		    break;
 		case ANYOF_NLOWER:
@@ -3664,7 +3650,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isLOWER(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsLower\n");
 		    break;
 		case ANYOF_PRINT:
@@ -3675,7 +3660,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isPRINT(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsPrint\n");
 		    break;
 		case ANYOF_NPRINT:
@@ -3686,7 +3670,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isPRINT(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsPrint\n");
 		    break;
 		case ANYOF_PSXSPC:
@@ -3697,7 +3680,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isPSXSPC(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsSpace\n");
 		    break;
 		case ANYOF_NPSXSPC:
@@ -3708,7 +3690,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isPSXSPC(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsSpace\n");
 		    break;
 		case ANYOF_PUNCT:
@@ -3719,7 +3700,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isPUNCT(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsPunct\n");
 		    break;
 		case ANYOF_NPUNCT:
@@ -3730,7 +3710,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isPUNCT(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsPunct\n");
 		    break;
 		case ANYOF_SPACE:
@@ -3741,7 +3720,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isSPACE(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsSpacePerl\n");
 		    break;
 		case ANYOF_NSPACE:
@@ -3752,7 +3730,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isSPACE(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsSpacePerl\n");
 		    break;
 		case ANYOF_UPPER:
@@ -3763,7 +3740,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isUPPER(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsUpper\n");
 		    break;
 		case ANYOF_NUPPER:
@@ -3774,7 +3750,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isUPPER(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsUpper\n");
 		    break;
 		case ANYOF_XDIGIT:
@@ -3785,7 +3760,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (isXDIGIT(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "+utf8::IsXDigit\n");
 		    break;
 		case ANYOF_NXDIGIT:
@@ -3796,7 +3770,6 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 			    if (!isXDIGIT(value))
 				ANYOF_BITMAP_SET(ret, value);
 		    }
-		    dont_optimize_invert = TRUE;
 		    Perl_sv_catpvf(aTHX_ listsv, "!utf8::IsXDigit\n");
 		    break;
 		default:
@@ -3810,17 +3783,18 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 	} /* end of namedclass \blah */
 
 	if (range) {
-	    if (((lastvalue > value) && !(PL_hints & HINT_RE_ASCIIR)) ||
-                ((NATIVE_TO_UNI(lastvalue) > NATIVE_TO_UNI(value)) && (PL_hints & HINT_RE_ASCIIR))) /* b-a */ {
+	    if (((prevvalue > value) && !(PL_hints & HINT_RE_ASCIIR)) ||
+                ((NATIVE_TO_UNI(prevvalue) > NATIVE_TO_UNI(value)) &&
+		 (PL_hints & HINT_RE_ASCIIR))) /* b-a */ {
 		Simple_vFAIL4("Invalid [] range \"%*.*s\"",
 			      RExC_parse - rangebegin,
 			      RExC_parse - rangebegin,
 			      rangebegin);
+		range = 0; /* not a valid range */
 	    }
-	    range = 0; /* not a true range */
 	}
 	else {
-	    lastvalue = value; /* save the beginning of the range */
+	    prevvalue = value; /* save the beginning of the range */
 	    if (*RExC_parse == '-' && RExC_parse+1 < RExC_end &&
 		RExC_parse[1] != ']') {
 		RExC_parse++;
@@ -3843,42 +3817,45 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
 
 	/* now is the next time */
 	if (!SIZE_ONLY) {
-	    if (lastvalue < 256 && value < 256) {
-#ifdef EBCDIC /* EBCDIC, for example. */
-		if (PL_hints & HINT_RE_ASCIIR) {
-		    IV i;
+	    IV i;
+
+	    if (prevvalue < 256) {
+	        IV ceilvalue = value < 256 ? value : 255;
+
+#ifdef EBCDIC
 		    /* New style scheme for ranges:
-		     * after :
 		     * use re 'asciir';
 		     * do ranges in ASCII/Unicode space
 		     */
-		    for (i = NATIVE_TO_ASCII(lastvalue) ; i <= NATIVE_TO_ASCII(value); i++)
-			ANYOF_BITMAP_SET(ret, ASCII_TO_NATIVE(i));
+		    for (i  = NATIVE_TO_ASCII(prevvalue);
+			 i <= NATIVE_TO_ASCII(ceilvalue);
+			 i++)
+		      ANYOF_BITMAP_SET(ret, ASCII_TO_NATIVE(i));
 		}
-		else if ((isLOWER(lastvalue) && isLOWER(value)) ||
-		    (isUPPER(lastvalue) && isUPPER(value)))
+		else if ((isLOWER(prevvalue) && isLOWER(ceilvalue)) ||
+			 (isUPPER(prevvalue) && isUPPER(ceilvalue)))
 		{
-		    IV i;
-		    if (isLOWER(lastvalue)) {
-			for (i = lastvalue; i <= value; i++)
+		    if (isLOWER(prevvalue)) {
+			for (i = prevvalue; i <= ceilvalue; i++)
 			    if (isLOWER(i))
 				ANYOF_BITMAP_SET(ret, i);
 		    } else {
-			for (i = lastvalue; i <= value; i++)
+			for (i = prevvalue; i <= ceilvalue; i++)
 			    if (isUPPER(i))
 				ANYOF_BITMAP_SET(ret, i);
 		    }
 		}
 		else
 #endif
-		    for ( ; lastvalue <= value; lastvalue++)
-			ANYOF_BITMAP_SET(ret, lastvalue);
-	    } else {
+		    for (i = prevvalue; i <= ceilvalue; i++)
+			ANYOF_BITMAP_SET(ret, i);
+	  }
+	  if (value > 255) {
 		ANYOF_FLAGS(ret) |= ANYOF_UNICODE;
-		if (lastvalue < value)
+		if (prevvalue < value)
 		    Perl_sv_catpvf(aTHX_ listsv, "%04"UVxf"\t%04"UVxf"\n",
-				   (UV)lastvalue, (UV)value);
-		else
+				   (UV)prevvalue, (UV)value);
+		else if (prevvalue == value)
 		    Perl_sv_catpvf(aTHX_ listsv, "%04"UVxf"\n",
 				   (UV)value);
 	    }
@@ -3912,7 +3889,7 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state)
     }
 
     /* optimize inverted simple patterns (e.g. [^a-z]) */
-    if (!SIZE_ONLY && !dont_optimize_invert &&
+    if (!SIZE_ONLY && optimize_invert &&
 	/* If the only flag is inversion. */
 	(ANYOF_FLAGS(ret) & ANYOF_FLAGS_ALL) ==	ANYOF_INVERT) {
 	for (value = 0; value < ANYOF_BITMAP_SIZE; ++value)
@@ -4448,7 +4425,7 @@ Perl_regprop(pTHX_ SV *sv, regnode *o)
 		    for (i = 0; i <= 256; i++) { /* just the first 256 */
 			U8 *e = uvchr_to_utf8(s, i);
 			
-			if (i < 256 && swash_fetch(sw, s)) {
+			if (i < 256 && swash_fetch(sw, s, TRUE)) {
 			    if (rangestart == -1)
 				rangestart = i;
 			} else if (rangestart != -1) {
diff --git a/regexec.c b/regexec.c
index e358d63d5f..c9096f0597 100644
--- a/regexec.c
+++ b/regexec.c
@@ -958,7 +958,7 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta
 		LOAD_UTF8_CHARCLASS(alnum,"a");
 		while (s < strend) {
 		    if (tmp == !(OP(c) == BOUND ?
-				 swash_fetch(PL_utf8_alnum, (U8*)s) :
+				 swash_fetch(PL_utf8_alnum, (U8*)s, do_utf8) :
 				 isALNUM_LC_utf8((U8*)s)))
 		    {
 			tmp = !tmp;
@@ -1001,7 +1001,7 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta
 		LOAD_UTF8_CHARCLASS(alnum,"a");
 		while (s < strend) {
 		    if (tmp == !(OP(c) == NBOUND ?
-				 swash_fetch(PL_utf8_alnum, (U8*)s) :
+				 swash_fetch(PL_utf8_alnum, (U8*)s, do_utf8) :
 				 isALNUM_LC_utf8((U8*)s)))
 			tmp = !tmp;
 		    else if ((norun || regtry(prog, s)))
@@ -1029,7 +1029,7 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta
 	    if (do_utf8) {
 		LOAD_UTF8_CHARCLASS(alnum,"a");
 		while (s < strend) {
-		    if (swash_fetch(PL_utf8_alnum, (U8*)s)) {
+		    if (swash_fetch(PL_utf8_alnum, (U8*)s, do_utf8)) {
 			if (tmp && (norun || regtry(prog, s)))
 			    goto got_it;
 			else
@@ -1087,7 +1087,7 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta
 	    if (do_utf8) {
 		LOAD_UTF8_CHARCLASS(alnum,"a");
 		while (s < strend) {
-		    if (!swash_fetch(PL_utf8_alnum, (U8*)s)) {
+		    if (!swash_fetch(PL_utf8_alnum, (U8*)s, do_utf8)) {
 			if (tmp && (norun || regtry(prog, s)))
 			    goto got_it;
 			else
@@ -1145,7 +1145,7 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta
 	    if (do_utf8) {
 		LOAD_UTF8_CHARCLASS(space," ");
 		while (s < strend) {
-		    if (*s == ' ' || swash_fetch(PL_utf8_space,(U8*)s)) {
+		    if (*s == ' ' || swash_fetch(PL_utf8_space,(U8*)s, do_utf8)) {
 			if (tmp && (norun || regtry(prog, s)))
 			    goto got_it;
 			else
@@ -1203,7 +1203,7 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta
 	    if (do_utf8) {
 		LOAD_UTF8_CHARCLASS(space," ");
 		while (s < strend) {
-		    if (!(*s == ' ' || swash_fetch(PL_utf8_space,(U8*)s))) {
+		    if (!(*s == ' ' || swash_fetch(PL_utf8_space,(U8*)s, do_utf8))) {
 			if (tmp && (norun || regtry(prog, s)))
 			    goto got_it;
 			else
@@ -1261,7 +1261,7 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta
 	    if (do_utf8) {
 		LOAD_UTF8_CHARCLASS(digit,"0");
 		while (s < strend) {
-		    if (swash_fetch(PL_utf8_digit,(U8*)s)) {
+		    if (swash_fetch(PL_utf8_digit,(U8*)s, do_utf8)) {
 			if (tmp && (norun || regtry(prog, s)))
 			    goto got_it;
 			else
@@ -1319,7 +1319,7 @@ S_find_byclass(pTHX_ regexp * prog, regnode *c, char *s, char *strend, char *sta
 	    if (do_utf8) {
 		LOAD_UTF8_CHARCLASS(digit,"0");
 		while (s < strend) {
-		    if (!swash_fetch(PL_utf8_digit,(U8*)s)) {
+		    if (!swash_fetch(PL_utf8_digit,(U8*)s, do_utf8)) {
 			if (tmp && (norun || regtry(prog, s)))
 			    goto got_it;
 			else
@@ -2214,7 +2214,7 @@ S_regmatch(pTHX_ regnode *prog)
 		sayNO;
 	    if (do_utf8) {
 		if (!(OP(scan) == ALNUM
-		      ? swash_fetch(PL_utf8_alnum, (U8*)locinput)
+		      ? swash_fetch(PL_utf8_alnum, (U8*)locinput, do_utf8)
 		      : isALNUM_LC_utf8((U8*)locinput)))
 		{
 		    sayNO;
@@ -2237,7 +2237,7 @@ S_regmatch(pTHX_ regnode *prog)
 	    if (do_utf8) {
 		LOAD_UTF8_CHARCLASS(alnum,"a");
 		if (OP(scan) == NALNUM
-		    ? swash_fetch(PL_utf8_alnum, (U8*)locinput)
+		    ? swash_fetch(PL_utf8_alnum, (U8*)locinput, do_utf8)
 		    : isALNUM_LC_utf8((U8*)locinput))
 		{
 		    sayNO;
@@ -2269,7 +2269,7 @@ S_regmatch(pTHX_ regnode *prog)
 		if (OP(scan) == BOUND || OP(scan) == NBOUND) {
 		    ln = isALNUM_uni(ln);
 		    LOAD_UTF8_CHARCLASS(alnum,"a");
-		    n = swash_fetch(PL_utf8_alnum, (U8*)locinput);
+		    n = swash_fetch(PL_utf8_alnum, (U8*)locinput, do_utf8);
 		}
 		else {
 		    ln = isALNUM_LC_uvchr(UNI_TO_NATIVE(ln));
@@ -2302,7 +2302,7 @@ S_regmatch(pTHX_ regnode *prog)
 		if (UTF8_IS_CONTINUED(nextchr)) {
 		    LOAD_UTF8_CHARCLASS(space," ");
 		    if (!(OP(scan) == SPACE
-			  ? swash_fetch(PL_utf8_space, (U8*)locinput)
+			  ? swash_fetch(PL_utf8_space, (U8*)locinput, do_utf8)
 			  : isSPACE_LC_utf8((U8*)locinput)))
 		    {
 			sayNO;
@@ -2332,7 +2332,7 @@ S_regmatch(pTHX_ regnode *prog)
 	    if (do_utf8) {
 		LOAD_UTF8_CHARCLASS(space," ");
 		if (OP(scan) == NSPACE
-		    ? swash_fetch(PL_utf8_space, (U8*)locinput)
+		    ? swash_fetch(PL_utf8_space, (U8*)locinput, do_utf8)
 		    : isSPACE_LC_utf8((U8*)locinput))
 		{
 		    sayNO;
@@ -2355,7 +2355,7 @@ S_regmatch(pTHX_ regnode *prog)
 	    if (do_utf8) {
 		LOAD_UTF8_CHARCLASS(digit,"0");
 		if (!(OP(scan) == DIGIT
-		      ? swash_fetch(PL_utf8_digit, (U8*)locinput)
+		      ? swash_fetch(PL_utf8_digit, (U8*)locinput, do_utf8)
 		      : isDIGIT_LC_utf8((U8*)locinput)))
 		{
 		    sayNO;
@@ -2378,7 +2378,7 @@ S_regmatch(pTHX_ regnode *prog)
 	    if (do_utf8) {
 		LOAD_UTF8_CHARCLASS(digit,"0");
 		if (OP(scan) == NDIGIT
-		    ? swash_fetch(PL_utf8_digit, (U8*)locinput)
+		    ? swash_fetch(PL_utf8_digit, (U8*)locinput, do_utf8)
 		    : isDIGIT_LC_utf8((U8*)locinput))
 		{
 		    sayNO;
@@ -2394,10 +2394,12 @@ S_regmatch(pTHX_ regnode *prog)
 	    break;
 	case CLUMP:
 	    LOAD_UTF8_CHARCLASS(mark,"~");
-	    if (locinput >= PL_regeol || swash_fetch(PL_utf8_mark,(U8*)locinput))
+	    if (locinput >= PL_regeol ||
+		swash_fetch(PL_utf8_mark,(U8*)locinput, do_utf8))
 		sayNO;
 	    locinput += PL_utf8skip[nextchr];
-	    while (locinput < PL_regeol && swash_fetch(PL_utf8_mark,(U8*)locinput))
+	    while (locinput < PL_regeol &&
+		   swash_fetch(PL_utf8_mark,(U8*)locinput, do_utf8))
 		locinput += UTF8SKIP(locinput);
 	    if (locinput > PL_regeol)
 		sayNO;
@@ -3623,7 +3625,7 @@ S_regrepeat(pTHX_ regnode *p, I32 max)
 	    loceol = PL_regeol;
 	    LOAD_UTF8_CHARCLASS(alnum,"a");
 	    while (hardcount < max && scan < loceol &&
-		   swash_fetch(PL_utf8_alnum, (U8*)scan)) {
+		   swash_fetch(PL_utf8_alnum, (U8*)scan, do_utf8)) {
 		scan += UTF8SKIP(scan);
 		hardcount++;
 	    }
@@ -3651,7 +3653,7 @@ S_regrepeat(pTHX_ regnode *p, I32 max)
 	    loceol = PL_regeol;
 	    LOAD_UTF8_CHARCLASS(alnum,"a");
 	    while (hardcount < max && scan < loceol &&
-		   !swash_fetch(PL_utf8_alnum, (U8*)scan)) {
+		   !swash_fetch(PL_utf8_alnum, (U8*)scan, do_utf8)) {
 		scan += UTF8SKIP(scan);
 		hardcount++;
 	    }
@@ -3679,7 +3681,8 @@ S_regrepeat(pTHX_ regnode *p, I32 max)
 	    loceol = PL_regeol;
 	    LOAD_UTF8_CHARCLASS(space," ");
 	    while (hardcount < max && scan < loceol &&
-		   (*scan == ' ' || swash_fetch(PL_utf8_space,(U8*)scan))) {
+		   (*scan == ' ' ||
+		    swash_fetch(PL_utf8_space,(U8*)scan, do_utf8))) {
 		scan += UTF8SKIP(scan);
 		hardcount++;
 	    }
@@ -3707,7 +3710,8 @@ S_regrepeat(pTHX_ regnode *p, I32 max)
 	    loceol = PL_regeol;
 	    LOAD_UTF8_CHARCLASS(space," ");
 	    while (hardcount < max && scan < loceol &&
-		   !(*scan == ' ' || swash_fetch(PL_utf8_space,(U8*)scan))) {
+		   !(*scan == ' ' ||
+		     swash_fetch(PL_utf8_space,(U8*)scan, do_utf8))) {
 		scan += UTF8SKIP(scan);
 		hardcount++;
 	    }
@@ -3735,7 +3739,7 @@ S_regrepeat(pTHX_ regnode *p, I32 max)
 	    loceol = PL_regeol;
 	    LOAD_UTF8_CHARCLASS(digit,"0");
 	    while (hardcount < max && scan < loceol &&
-		   swash_fetch(PL_utf8_digit,(U8*)scan)) {
+		   swash_fetch(PL_utf8_digit, (U8*)scan, do_utf8)) {
 		scan += UTF8SKIP(scan);
 		hardcount++;
 	    }
@@ -3749,7 +3753,7 @@ S_regrepeat(pTHX_ regnode *p, I32 max)
 	    loceol = PL_regeol;
 	    LOAD_UTF8_CHARCLASS(digit,"0");
 	    while (hardcount < max && scan < loceol &&
-		   !swash_fetch(PL_utf8_digit,(U8*)scan)) {
+		   !swash_fetch(PL_utf8_digit, (U8*)scan, do_utf8)) {
 		scan += UTF8SKIP(scan);
 		hardcount++;
 	    }
@@ -3879,25 +3883,22 @@ S_reginclass(pTHX_ register regnode *n, register U8* p, register bool do_utf8)
     char flags = ANYOF_FLAGS(n);
     bool match = FALSE;
     UV c;
-    STRLEN len;
+    STRLEN len = 0;
 
-    if (do_utf8)
-	c = utf8_to_uvchr(p, &len);
-    else
-	c = *p;
+    c = do_utf8 ? utf8_to_uvchr(p, &len) : *p;
 
     if (do_utf8 || (flags & ANYOF_UNICODE)) {
 	if (do_utf8 && !ANYOF_RUNTIME(n)) {
 	    if (len != (STRLEN)-1 && c < 256 && ANYOF_BITMAP_TEST(n, c))
 		match = TRUE;
 	}
-	if (do_utf8 && flags & ANYOF_UNICODE_ALL && c >= 256)
+	if (!match && do_utf8 && (flags & ANYOF_UNICODE_ALL) && c >= 256)
 	    match = TRUE;
 	if (!match) {
 	    SV *sw = regclass_swash(n, TRUE, 0);
 	
 	    if (sw) {
-		if (swash_fetch(sw, p))
+		if (swash_fetch(sw, p, do_utf8))
 		    match = TRUE;
 		else if (flags & ANYOF_FOLD) {
 		    U8 tmpbuf[UTF8_MAXLEN+1];
@@ -3908,7 +3909,7 @@ S_reginclass(pTHX_ register regnode *n, register U8* p, register bool do_utf8)
 		    }
 		    else
 		        uvchr_to_utf8(tmpbuf, toLOWER_utf8(p));
-		    if (swash_fetch(sw, tmpbuf))
+		    if (swash_fetch(sw, tmpbuf, do_utf8))
 			match = TRUE;
 		}
 	    }
@@ -3918,7 +3919,7 @@ S_reginclass(pTHX_ register regnode *n, register U8* p, register bool do_utf8)
 	if (ANYOF_BITMAP_TEST(n, c))
 	    match = TRUE;
 	else if (flags & ANYOF_FOLD) {
-	    I32 f;
+	  I32 f;
 
 	    if (flags & ANYOF_LOCALE) {
 		PL_reg_flags |= RF_tainted;
diff --git a/t/lib/b-deparse.t b/t/lib/b-deparse.t
index 1f9bdb75b0..24ff3279b1 100644
--- a/t/lib/b-deparse.t
+++ b/t/lib/b-deparse.t
@@ -124,8 +124,8 @@ my $foo = $deparse->coderef2text(sub { { 234; }});
 print "not " unless $foo =~ /{.*{.*234;.*}.*}/sm;
 ok;
 $foo = $deparse->coderef2text(sub { { 234; } continue { 123; } });
-unless ($foo =~ /{\s*{\s*234;\s*}\s*continue\s*{\s*123;\s*}/sm) {
-  print "# [$foo]\n\# vs expected\n# [sub { { 234; } continue { 123; } }]\n";
+unless ($foo =~ /{\s*{\s*do\s*{\s*234;\s*};\s*}\s*continue\s*{\s*123;\s*}\s*}/sm) {
+  print "# [$foo]\n\# vs expected\n# [{ { do { 234; }; } continue { 123; } }]\n";
   print "not ";
 }
 ok;
diff --git a/t/lib/selfstubber.t b/t/lib/selfstubber.t
index d338489599..fd0cf0640e 100644
--- a/t/lib/selfstubber.t
+++ b/t/lib/selfstubber.t
@@ -10,10 +10,6 @@ use Devel::SelfStubber;
 
 my $runperl = "$^X \"-I../lib\"";
 
-# ensure correct output ordering for system() calls
-
-select STDERR; $| = 1; select STDOUT; $| = 1;
-
 print "1..12\n";
 
 my @cleanup;
diff --git a/t/op/pat.t b/t/op/pat.t
index 9130454dcb..1be72346f8 100755
--- a/t/op/pat.t
+++ b/t/op/pat.t
@@ -5,7 +5,8 @@
 # that does fit that format, add it to op/re_tests, not here.
 
 $| = 1;
-print "1..587\n";
+
+print "1..615\n";
 
 BEGIN {
     chdir 't' if -d 't';
@@ -1302,6 +1303,7 @@ print "ok 247\n";
 {
     # the second half of 20001028.003
 
+    my $X = '';
     $X =~ s/^/chr(1488)/e;
     print "not " unless length $X == 1 && ord($X) == 1488;
     print "ok 260\n";
@@ -1353,10 +1355,11 @@ print "ok 247\n";
 	     "\0"				=> 'Cc',
 	     );
 	
-    for my $char (keys %s) {
+    for my $char (map { s/^\S+ //; $_ }
+                    sort map { sprintf("%06x", ord($_))." $_" } keys %s) {
 	my $class = $s{$char};
-	my $code  = sprintf("%04x", ord($char));
-	printf "# 0x$code\n";
+	my $code  = sprintf("%06x", ord($char));
+	printf "#\n# 0x$code\n#\n";
 	print "# IsAlpha\n";
 	if ($class =~ /^[LM]/) {
 	    print "not " unless $char =~ /\p{IsAlpha}/;
@@ -1382,7 +1385,7 @@ print "ok 247\n";
 	    print "ok $test\n"; $test++;
 	}
 	print "# IsASCII\n";
-	if ($code <= 127) {
+	if ($code le '00007f') {
 	    print "not " unless $char =~ /\p{IsASCII}/;
 	    print "ok $test\n"; $test++;
 	    print "not " if     $char =~ /\P{IsASCII}/;
@@ -1583,3 +1586,104 @@ EOT
     print "not " unless ord($x) == 0x12345678 && length($x) == 1;
     print "ok 587\n";
 }
+
+{
+    my $x = "\x7f";
+
+    print "not " if     $x =~ /[\x80-\xff]/;
+    print "ok 588\n";
+
+    print "not " if     $x =~ /[\x80-\x{100}]/;
+    print "ok 589\n";
+
+    print "not " if     $x =~ /[\x{100}]/;
+    print "ok 590\n";
+
+    print "not " if     $x =~ /\p{InLatin1Supplement}/;
+    print "ok 591\n";
+
+    print "not " unless $x =~ /\P{InLatin1Supplement}/;
+    print "ok 592\n";
+
+    print "not " if     $x =~ /\p{InLatinExtendedA}/;
+    print "ok 593\n";
+
+    print "not " unless $x =~ /\P{InLatinExtendedA}/;
+    print "ok 594\n";
+}
+
+{
+    my $x = "\x80";
+
+    print "not " unless $x =~ /[\x80-\xff]/;
+    print "ok 595\n";
+
+    print "not " unless $x =~ /[\x80-\x{100}]/;
+    print "ok 596\n";
+
+    print "not " if     $x =~ /[\x{100}]/;
+    print "ok 597\n";
+
+    print "not " unless $x =~ /\p{InLatin1Supplement}/;
+    print "ok 598\n";
+
+    print "not " if    $x =~ /\P{InLatin1Supplement}/;
+    print "ok 599\n";
+
+    print "not " if     $x =~ /\p{InLatinExtendedA}/;
+    print "ok 600\n";
+
+    print "not " unless $x =~ /\P{InLatinExtendedA}/;
+    print "ok 601\n";
+}
+
+{
+    my $x = "\xff";
+
+    print "not " unless $x =~ /[\x80-\xff]/;
+    print "ok 602\n";
+
+    print "not " unless $x =~ /[\x80-\x{100}]/;
+    print "ok 603\n";
+
+    print "not " if     $x =~ /[\x{100}]/;
+    print "ok 604\n";
+
+    print "not " unless $x =~ /\p{InLatin1Supplement}/;
+    print "ok 605\n";
+
+    print "not " if     $x =~ /\P{InLatin1Supplement}/;
+    print "ok 606\n";
+
+    print "not " if     $x =~ /\p{InLatinExtendedA}/;
+    print "ok 607\n";
+
+    print "not " unless $x =~ /\P{InLatinExtendedA}/;
+    print "ok 608\n";
+}
+
+{
+    my $x = "\x{100}";
+
+    print "not " if     $x =~ /[\x80-\xff]/;
+    print "ok 609\n";
+
+    print "not " unless $x =~ /[\x80-\x{100}]/;
+    print "ok 610\n";
+
+    print "not " unless $x =~ /[\x{100}]/;
+    print "ok 611\n";
+
+    print "not " if     $x =~ /\p{InLatin1Supplement}/;
+    print "ok 612\n";
+
+    print "not " unless $x =~ /\P{InLatin1Supplement}/;
+    print "ok 613\n";
+
+    print "not " unless $x =~ /\p{InLatinExtendedA}/;
+    print "ok 614\n";
+
+    print "not " if     $x =~ /\P{InLatinExtendedA}/;
+    print "ok 615\n";
+}
+
diff --git a/utf8.c b/utf8.c
index fda9920933..b682cf65ca 100644
--- a/utf8.c
+++ b/utf8.c
@@ -1045,13 +1045,13 @@ Perl_is_utf8_alnum(pTHX_ U8 *p)
 	 * descendant of isalnum(3), in other words, it doesn't
 	 * contain the '_'. --jhi */
 	PL_utf8_alnum = swash_init("utf8", "IsWord", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_alnum, p);
+    return swash_fetch(PL_utf8_alnum, p, TRUE);
 /*    return *p == '_' || is_utf8_alpha(p) || is_utf8_digit(p); */
 #ifdef SURPRISINGLY_SLOWER  /* probably because alpha is usually true */
     if (!PL_utf8_alnum)
 	PL_utf8_alnum = swash_init("utf8", "",
 	    sv_2mortal(newSVpv("+utf8::IsAlpha\n+utf8::IsDigit\n005F\n",0)), 0, 0);
-    return swash_fetch(PL_utf8_alnum, p);
+    return swash_fetch(PL_utf8_alnum, p, TRUE);
 #endif
 }
 
@@ -1062,13 +1062,13 @@ Perl_is_utf8_alnumc(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_alnum)
 	PL_utf8_alnum = swash_init("utf8", "IsAlnumC", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_alnum, p);
+    return swash_fetch(PL_utf8_alnum, p, TRUE);
 /*    return is_utf8_alpha(p) || is_utf8_digit(p); */
 #ifdef SURPRISINGLY_SLOWER  /* probably because alpha is usually true */
     if (!PL_utf8_alnum)
 	PL_utf8_alnum = swash_init("utf8", "",
 	    sv_2mortal(newSVpv("+utf8::IsAlpha\n+utf8::IsDigit\n005F\n",0)), 0, 0);
-    return swash_fetch(PL_utf8_alnum, p);
+    return swash_fetch(PL_utf8_alnum, p, TRUE);
 #endif
 }
 
@@ -1085,7 +1085,7 @@ Perl_is_utf8_alpha(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_alpha)
 	PL_utf8_alpha = swash_init("utf8", "IsAlpha", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_alpha, p);
+    return swash_fetch(PL_utf8_alpha, p, TRUE);
 }
 
 bool
@@ -1095,7 +1095,7 @@ Perl_is_utf8_ascii(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_ascii)
 	PL_utf8_ascii = swash_init("utf8", "IsAscii", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_ascii, p);
+    return swash_fetch(PL_utf8_ascii, p, TRUE);
 }
 
 bool
@@ -1105,7 +1105,7 @@ Perl_is_utf8_space(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_space)
 	PL_utf8_space = swash_init("utf8", "IsSpacePerl", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_space, p);
+    return swash_fetch(PL_utf8_space, p, TRUE);
 }
 
 bool
@@ -1115,7 +1115,7 @@ Perl_is_utf8_digit(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_digit)
 	PL_utf8_digit = swash_init("utf8", "IsDigit", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_digit, p);
+    return swash_fetch(PL_utf8_digit, p, TRUE);
 }
 
 bool
@@ -1125,7 +1125,7 @@ Perl_is_utf8_upper(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_upper)
 	PL_utf8_upper = swash_init("utf8", "IsUpper", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_upper, p);
+    return swash_fetch(PL_utf8_upper, p, TRUE);
 }
 
 bool
@@ -1135,7 +1135,7 @@ Perl_is_utf8_lower(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_lower)
 	PL_utf8_lower = swash_init("utf8", "IsLower", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_lower, p);
+    return swash_fetch(PL_utf8_lower, p, TRUE);
 }
 
 bool
@@ -1145,7 +1145,7 @@ Perl_is_utf8_cntrl(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_cntrl)
 	PL_utf8_cntrl = swash_init("utf8", "IsCntrl", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_cntrl, p);
+    return swash_fetch(PL_utf8_cntrl, p, TRUE);
 }
 
 bool
@@ -1155,7 +1155,7 @@ Perl_is_utf8_graph(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_graph)
 	PL_utf8_graph = swash_init("utf8", "IsGraph", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_graph, p);
+    return swash_fetch(PL_utf8_graph, p, TRUE);
 }
 
 bool
@@ -1165,7 +1165,7 @@ Perl_is_utf8_print(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_print)
 	PL_utf8_print = swash_init("utf8", "IsPrint", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_print, p);
+    return swash_fetch(PL_utf8_print, p, TRUE);
 }
 
 bool
@@ -1175,7 +1175,7 @@ Perl_is_utf8_punct(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_punct)
 	PL_utf8_punct = swash_init("utf8", "IsPunct", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_punct, p);
+    return swash_fetch(PL_utf8_punct, p, TRUE);
 }
 
 bool
@@ -1185,7 +1185,7 @@ Perl_is_utf8_xdigit(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_xdigit)
 	PL_utf8_xdigit = swash_init("utf8", "IsXDigit", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_xdigit, p);
+    return swash_fetch(PL_utf8_xdigit, p, TRUE);
 }
 
 bool
@@ -1195,7 +1195,7 @@ Perl_is_utf8_mark(pTHX_ U8 *p)
 	return FALSE;
     if (!PL_utf8_mark)
 	PL_utf8_mark = swash_init("utf8", "IsM", &PL_sv_undef, 0, 0);
-    return swash_fetch(PL_utf8_mark, p);
+    return swash_fetch(PL_utf8_mark, p, TRUE);
 }
 
 UV
@@ -1205,7 +1205,7 @@ Perl_to_utf8_upper(pTHX_ U8 *p)
 
     if (!PL_utf8_toupper)
 	PL_utf8_toupper = swash_init("utf8", "ToUpper", &PL_sv_undef, 4, 0);
-    uv = swash_fetch(PL_utf8_toupper, p);
+    uv = swash_fetch(PL_utf8_toupper, p, TRUE);
     return uv ? UNI_TO_NATIVE(uv) : utf8_to_uvchr(p,0);
 }
 
@@ -1216,7 +1216,7 @@ Perl_to_utf8_title(pTHX_ U8 *p)
 
     if (!PL_utf8_totitle)
 	PL_utf8_totitle = swash_init("utf8", "ToTitle", &PL_sv_undef, 4, 0);
-    uv = swash_fetch(PL_utf8_totitle, p);
+    uv = swash_fetch(PL_utf8_totitle, p, TRUE);
     return uv ? UNI_TO_NATIVE(uv) : utf8_to_uvchr(p,0);
 }
 
@@ -1227,7 +1227,7 @@ Perl_to_utf8_lower(pTHX_ U8 *p)
 
     if (!PL_utf8_tolower)
 	PL_utf8_tolower = swash_init("utf8", "ToLower", &PL_sv_undef, 4, 0);
-    uv = swash_fetch(PL_utf8_tolower, p);
+    uv = swash_fetch(PL_utf8_tolower, p, TRUE);
     return uv ? UNI_TO_NATIVE(uv) : utf8_to_uvchr(p,0);
 }
 
@@ -1282,21 +1282,31 @@ Perl_swash_init(pTHX_ char* pkg, char* name, SV *listsv, I32 minbits, I32 none)
 }
 
 UV
-Perl_swash_fetch(pTHX_ SV *sv, U8 *ptr)
+Perl_swash_fetch(pTHX_ SV *sv, U8 *ptr, bool do_utf8)
 {
     HV* hv = (HV*)SvRV(sv);
-    /* Given a UTF-X encoded char 0xAA..0xYY,0xZZ
-       then the "swatch" is a vec() for al the chars which start
-       with 0xAA..0xYY
-       So the key in the hash is length of encoded char -1
-     */
-    U32 klen = UTF8SKIP(ptr) - 1;
-    U32 off = ptr[klen];
+    U32 klen;
+    U32 off;
     STRLEN slen;
     STRLEN needents;
     U8 *tmps;
     U32 bit;
     SV *retval;
+    U8 tmputf8[2];
+    UV c = NATIVE_TO_ASCII(*ptr);
+
+    if (!do_utf8 && !UNI_IS_INVARIANT(c)) {
+        tmputf8[0] = UTF8_EIGHT_BIT_HI(c);
+        tmputf8[1] = UTF8_EIGHT_BIT_LO(c);
+        ptr = tmputf8;
+    }
+    /* Given a UTF-X encoded char 0xAA..0xYY,0xZZ
+     * then the "swatch" is a vec() for al the chars which start
+     * with 0xAA..0xYY
+     * So the key in the hash (klen) is length of encoded char -1
+     */
+    klen = UTF8SKIP(ptr) - 1;
+    off  = ptr[klen];
 
     if (klen == 0)
      {
@@ -1322,9 +1332,9 @@ Perl_swash_fetch(pTHX_ SV *sv, U8 *ptr)
      * NB: this code assumes that swatches are never modified, once generated!
      */
 
-    if (hv == PL_last_swash_hv &&
+    if (hv   == PL_last_swash_hv &&
 	klen == PL_last_swash_klen &&
-	(!klen || memEQ((char *)ptr,(char *)PL_last_swash_key,klen)) )
+	(!klen || memEQ((char *)ptr, (char *)PL_last_swash_key, klen)) )
     {
 	tmps = PL_last_swash_tmps;
 	slen = PL_last_swash_slen;
@@ -1348,7 +1358,8 @@ Perl_swash_fetch(pTHX_ SV *sv, U8 *ptr)
 	    EXTEND(SP,3);
 	    PUSHs((SV*)sv);
 	    /* On EBCDIC & ~(0xA0-1) isn't a useful thing to do */
-	    PUSHs(sv_2mortal(newSViv((klen) ? (code_point & ~(needents - 1)) : 0)));
+	    PUSHs(sv_2mortal(newSViv((klen) ?
+				     (code_point & ~(needents - 1)) : 0)));
 	    PUSHs(sv_2mortal(newSViv(needents)));
 	    PUTBACK;
 	    if (call_method("SWASHGET", G_SCALAR))
diff --git a/win32/Makefile b/win32/Makefile
index 15aa5de183..ccab8b5af7 100644
--- a/win32/Makefile
+++ b/win32/Makefile
@@ -609,7 +609,8 @@ SETARGV_OBJ	= setargv$(o)
 DYNAMIC_EXT	= Socket IO Fcntl Opcode SDBM_File POSIX attrs Thread B re \
 		Data/Dumper Devel/Peek ByteLoader Devel/DProf File/Glob \
 		Sys/Hostname Storable Filter/Util/Call Encode Digest/MD5 \
-		PerlIO/Scalar MIME/Base64 Time/HiRes Time/Piece
+		PerlIO/Scalar MIME/Base64 Time/HiRes Time/Piece \
+		Cwd List/Util PerlIO/Via XS/Typemap
 STATIC_EXT	= DynaLoader
 NONXS_EXT	= Errno
 
@@ -639,6 +640,13 @@ PERLIOSCALAR	= $(EXTDIR)\PerlIO\Scalar\Scalar
 MIMEBASE64	= $(EXTDIR)\MIME\Base64\Base64
 TIMEHIRES	= $(EXTDIR)\Time\HiRes\HiRes
 TIMEPIECE	= $(EXTDIR)\Time\Piece\Piece
+CWD		= $(EXTDIR)\Cwd\Cwd
+LISTUTIL  	= $(EXTDIR)\List\Util\Util
+PERLIOVIA	= $(EXTDIR)\PerlIO\Via\Via
+XSTYPEMAP	= $(EXTDIR)\XS\Typemap\Typemap
+
+# Help out FindExt::scan_ext() with a copy
+LISTUTIL_PM	= $(LISTUTIL).pm
 
 SOCKET_DLL	= $(AUTODIR)\Socket\Socket.dll
 FCNTL_DLL	= $(AUTODIR)\Fcntl\Fcntl.dll
@@ -664,6 +672,10 @@ PERLIOSCALAR_DLL= $(AUTODIR)\PerlIO\Scalar\Scalar.dll
 MIMEBASE64_DLL	= $(AUTODIR)\MIME\Base64\Base64.dll
 TIMEHIRES_DLL	= $(AUTODIR)\Time\HiRes\HiRes.dll
 TIMEPIECE_DLL	= $(AUTODIR)\Time\Piece\Piece.dll
+CWD_DLL		= $(AUTODIR)\Cwd\Cwd.dll
+LISTUTIL_DLL	= $(AUTODIR)\List\Util\Util.dll
+PERLIOVIA_DLL	= $(AUTODIR)\PerlIO\Via\Via.dll
+XSTYPEMAP_DLL	= $(AUTODIR)\XS\Typemap\Typemap.dll
 
 ERRNO_PM	= $(LIBDIR)\Errno.pm
 
@@ -691,7 +703,11 @@ EXTENSION_C	= 		\
 		$(PERLIOSCALAR).c	\
 		$(MIMEBASE64).c	\
 		$(TIMEHIRES).c	\
-		$(TIMEPIECE).c	
+		$(TIMEPIECE).c	\
+		$(CWD).c	\
+		$(LISTUTIL).c	\
+		$(PERLIOVIA).c	\
+		$(XSTYPEMAP).c
 
 EXTENSION_DLL	= 		\
 		$(SOCKET_DLL)	\
@@ -717,7 +733,11 @@ EXTENSION_DLL	= 		\
 		$(PERLIOSCALAR_DLL) \
 		$(MIMEBASE64_DLL) \
 		$(TIMEHIRES_DLL)  \
-		$(TIMEPIECE_DLL)
+		$(TIMEPIECE_DLL)  \
+		$(CWD_DLL)	\
+		$(LISTUTIL_DLL)	\
+		$(PERLIOVIA_DLL)	\
+		$(XSTYPEMAP_DLL)
 
 EXTENSION_PM	=		\
 		$(ERRNO_PM)
@@ -780,7 +800,7 @@ config.w32 : $(CFGSH_TMPL)
 	-del /f config.h
 	copy $(CFGH_TMPL) config.h
 
-..\config.sh : config.w32 $(MINIPERL) config_sh.PL
+..\config.sh : config.w32 $(MINIPERL) $(LISTUTIL_PM) config_sh.PL
 	$(MINIPERL) -I..\lib config_sh.PL $(CFG_VARS) config.w32 > ..\config.sh
 
 # this target is for when changes to the main config.sh happen
@@ -1020,35 +1040,64 @@ $(ENCODE_DLL): $(PERLEXE) $(ENCODE).xs
 	cd ..\..\win32
 
 $(MD5_DLL): $(PERLEXE) $(MD5).xs
-	cd $(EXTDIR)\$(*B)
-	..\..\miniperl -I..\..\lib Makefile.PL INSTALLDIRS=perl
+	cd $(EXTDIR)\Digest\$(*B)
+	..\..\..\miniperl -I..\..\..\lib Makefile.PL INSTALLDIRS=perl
 	$(MAKE)
-	cd ..\..\win32
+	cd ..\..\..\win32
 
 $(PERLIOSCALAR_DLL): $(PERLEXE) $(PERLIOSCALAR).xs
-	cd $(EXTDIR)\$(*B)
-	..\..\miniperl -I..\..\lib Makefile.PL INSTALLDIRS=perl
+	cd $(EXTDIR)\PerlIO\$(*B)
+	..\..\..\miniperl -I..\..\..\lib Makefile.PL INSTALLDIRS=perl
 	$(MAKE)
-	cd ..\..\win32
+	cd ..\..\..\win32
 
 $(MIMEBASE64_DLL): $(PERLEXE) $(MIMEBASE64).xs
-	cd $(EXTDIR)\$(*B)
-	..\..\miniperl -I..\..\lib Makefile.PL INSTALLDIRS=perl
+	cd $(EXTDIR)\MIME\$(*B)
+	..\..\..\miniperl -I..\..\..\lib Makefile.PL INSTALLDIRS=perl
 	$(MAKE)
-	cd ..\..\win32
+	cd ..\..\..\win32
 
 $(TIMEHIRES_DLL): $(PERLEXE) $(TIMEHIRES).xs
-	cd $(EXTDIR)\$(*B)
-	..\..\miniperl -I..\..\lib Makefile.PL INSTALLDIRS=perl
+	cd $(EXTDIR)\Time\$(*B)
+	..\..\..\miniperl -I..\..\..\lib Makefile.PL INSTALLDIRS=perl
 	$(MAKE)
-	cd ..\..\win32
+	cd ..\..\..\win32
 
 $(TIMEPIECE_DLL): $(PERLEXE) $(TIMEPIECE).xs
+	cd $(EXTDIR)\Time\$(*B)
+	..\..\..\miniperl -I..\..\..\lib Makefile.PL INSTALLDIRS=perl
+	$(MAKE)
+	cd ..\..\..\win32
+
+$(CWD_DLL): $(PERLEXE) $(CWD).xs
 	cd $(EXTDIR)\$(*B)
 	..\..\miniperl -I..\..\lib Makefile.PL INSTALLDIRS=perl
 	$(MAKE)
 	cd ..\..\win32
 
+$(LISTUTIL_PM): $(EXTDIR)\List\Util\lib\List\Util.pm
+	cd $(EXTDIR)
+	copy List\Util\lib\List\Util.pm List\Util\Util.pm
+	cd ..\win32
+
+$(LISTUTIL_DLL): $(LISTUTIL_PM) $(PERLEXE) $(LISTUTIL).xs
+	cd $(EXTDIR)\List\$(*B)
+	..\..\..\miniperl -I..\..\..\lib Makefile.PL INSTALLDIRS=perl
+	$(MAKE)
+	cd ..\..\..\win32
+
+$(PERLIOVIA_DLL): $(PERLEXE) $(PERLIOVIA).xs
+	cd $(EXTDIR)\PerlIO\$(*B)
+	..\..\..\miniperl -I..\..\..\lib Makefile.PL INSTALLDIRS=perl
+	$(MAKE)
+	cd ..\..\..\win32
+
+$(XSTYPEMAP_DLL): $(PERLEXE) $(XSTYPEMAP).xs
+	cd $(EXTDIR)\XS\$(*B)
+	..\..\..\miniperl -I..\..\..\lib Makefile.PL INSTALLDIRS=perl
+	$(MAKE)
+	cd ..\..\..\win32
+
 $(ERRNO_PM): $(PERLEXE) $(ERRNO)_pm.PL
 	cd $(EXTDIR)\$(*B)
 	..\..\miniperl -I..\..\lib Makefile.PL INSTALLDIRS=perl
@@ -1107,12 +1156,16 @@ distclean: clean
 	-del /f $(LIBDIR)\Filter\Util\Call.pm
 	-del /f $(LIBDIR)\Digest\MD5.pm
 	-del /f $(LIBDIR)\PerlIO\Scalar.pm
+	-del /f $(LIBDIR)\PerlIO\Via.pm
 	-del /f $(LIBDIR)\MIME\Base64.pm
 	-del /f $(LIBDIR)\MIME\QuotedPrint.pm
 	-del /f $(LIBDIR)\List\Util.pm
+	-del /f $(LISTUTIL_PM)
 	-del /f $(LIBDIR)\Scalar\Util.pm
 	-del /f $(LIBDIR)\Time\HiRes.pm
 	-del /f $(LIBDIR)\Time\Piece.pm
+	-del /f $(LIBDIR)\Cwd.pm
+	-del /f $(LIBDIR)\XS\Typemap.pm
 	-if exist $(LIBDIR)\IO rmdir /s /q $(LIBDIR)\IO
 	-rmdir /s $(LIBDIR)\IO
 	-if exist $(LIBDIR)\Thread rmdir /s /q $(LIBDIR)\Thread
@@ -1130,6 +1183,8 @@ distclean: clean
 	-rmdir /s $(LIBDIR)\List
 	-if exist $(LIBDIR)\Scalar rmdir /s /q $(LIBDIR)\Scalar
 	-rmdir /s $(LIBDIR)\Scalar
+	-if exist $(LIBDIR)\XS rmdir /s /q $(LIBDIR)\XS
+	-rmdir /s $(LIBDIR)\XS
 	cd $(PODDIR)
 	-del /f *.html *.bat checkpods \
 	    perlaix.pod perlamiga.pod perlbs2000.pod perlcygwin.pod \